abhinavp's picture
Training in progress, epoch 1, checkpoint
aca10ad verified
{
"best_metric": 3.8435018062591553,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/transformer/0/checkpoints/checkpoint-992160",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 1831680,
"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": 11.0716,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8178,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1789,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9638,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8051,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7015,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5961,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5295,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.443,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.394,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3468,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3168,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2648,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.207,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1786,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1281,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1107,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0866,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0455,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0206,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0064,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9814,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9536,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9364,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9265,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8883,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8745,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8662,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8361,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8155,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8067,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.7988,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7873,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7693,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7594,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7544,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7355,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7073,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.7047,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6781,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6881,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6735,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6737,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.651,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6525,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6378,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6303,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 4.6343,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.5939,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.6027,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6044,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5979,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5743,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5678,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5581,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5511,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5665,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5278,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5439,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5351,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5147,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5243,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5009,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4971,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4965,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5061,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4754,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.477,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4611,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4721,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4763,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4722,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4518,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4632,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4676,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4437,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4387,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4312,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4246,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4315,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4118,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4329,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4246,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.409,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3917,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4022,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4009,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4046,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3887,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3909,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3855,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3725,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3701,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3764,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3696,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3706,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.356,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3548,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3616,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3614,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3526,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3477,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3397,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.337,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3388,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3149,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3259,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3287,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3291,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3154,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.323,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3009,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3287,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.2987,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3094,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3084,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3127,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3036,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2941,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.296,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2977,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.286,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2855,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2803,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.3006,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2688,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2736,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2704,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2746,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2656,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2825,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2711,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2652,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2564,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2692,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2632,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.268,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.251,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2638,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.257,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2593,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2392,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2586,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2413,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2246,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2548,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2397,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2392,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2391,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2253,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.196438789367676,
"eval_runtime": 307.708,
"eval_samples_per_second": 1240.107,
"eval_steps_per_second": 38.754,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2071,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.214,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2336,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2178,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2242,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2149,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2083,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2023,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2068,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2046,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2181,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2123,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.1969,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1897,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1837,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1822,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1937,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1828,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1803,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.1983,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1854,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1805,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1826,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1941,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1654,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1697,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1795,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1687,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1574,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1576,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1713,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1664,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1643,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1609,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1624,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1604,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1454,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1496,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1348,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1481,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.1425,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.1545,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1399,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1465,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1411,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.1406,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1511,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1178,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1294,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.144,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1388,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1253,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1196,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1202,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1098,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.1345,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1082,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1276,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1209,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1081,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.1152,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1036,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.1026,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.106,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.1236,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.094,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.1017,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.0848,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172567731267074e-05,
"loss": 4.1011,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.115,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1075,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0981,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813904032002872e-05,
"loss": 4.108,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1127,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.0948,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.0925,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810551290879037e-05,
"loss": 4.0932,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.0881,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.0934,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0855,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0997,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0941,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0892,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.071,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0817,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803005575999943e-05,
"loss": 4.0886,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0901,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0832,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.0795,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996528348761076e-05,
"loss": 4.084,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988158780054285e-05,
"loss": 4.0721,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979772832543765e-05,
"loss": 4.0664,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971386885033245e-05,
"loss": 4.0825,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963000937522725e-05,
"loss": 4.0743,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.0787,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0725,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0628,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.0769,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.0814,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0692,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0665,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.0588,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.0642,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0714,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0482,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786241870380768e-05,
"loss": 4.0549,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854032756297166e-05,
"loss": 4.0606,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0682,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.052,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0605,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0471,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0681,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0478,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0544,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0627,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0598,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0565,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0447,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0508,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.0552,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773669500636481e-05,
"loss": 4.0425,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772830905885429e-05,
"loss": 4.0452,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771992311134377e-05,
"loss": 4.0411,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771153716383325e-05,
"loss": 4.06,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0337,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0418,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0369,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0436,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0344,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0538,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0493,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0373,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763611277264976e-05,
"loss": 4.0296,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762772682513924e-05,
"loss": 4.0455,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0428,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.051,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.0259,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759419941390089e-05,
"loss": 4.0466,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.038,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.049,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.0288,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.04,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0316,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0206,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0414,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0337,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0305,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0272,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0228,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.0265703201293945,
"eval_runtime": 314.4532,
"eval_samples_per_second": 1213.507,
"eval_steps_per_second": 37.923,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749360080138211e-05,
"loss": 4.0037,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748521485387159e-05,
"loss": 4.0115,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747682890636107e-05,
"loss": 4.0349,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746844295885055e-05,
"loss": 4.0202,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746005701134003e-05,
"loss": 4.0281,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745167106382951e-05,
"loss": 4.0129,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744328511631899e-05,
"loss": 4.0132,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434899168808475e-05,
"loss": 4.0075,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426513221297955e-05,
"loss": 4.0132,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418127273787435e-05,
"loss": 4.0168,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740974132627691e-05,
"loss": 4.0213,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0233,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.0082,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 4.0021,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 4.0025,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 3.992,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 4.0056,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 3.9989,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 3.9985,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733431693509343e-05,
"loss": 4.0203,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732593098758291e-05,
"loss": 4.0024,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731754504007238e-05,
"loss": 4.0041,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730915909256186e-05,
"loss": 4.0073,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730078952385508e-05,
"loss": 4.0162,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729240357634456e-05,
"loss": 3.9866,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728401762883403e-05,
"loss": 3.9979,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727563168132351e-05,
"loss": 4.0037,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 3.9973,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725887616510621e-05,
"loss": 3.9875,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725049021759568e-05,
"loss": 3.9823,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 4.0031,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 4.0017,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 3.9925,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9971,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9938,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200190911336296e-05,
"loss": 3.9915,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191804963825775e-05,
"loss": 3.9811,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183419016315255e-05,
"loss": 3.9909,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9686,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166663500097945e-05,
"loss": 3.9866,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158277552587424e-05,
"loss": 3.983,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149891605076904e-05,
"loss": 3.9946,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9815,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9834,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9876,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9818,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.993,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9611,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9783,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.9846,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707446721389342e-05,
"loss": 3.9865,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9713,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705771169767611e-05,
"loss": 3.9643,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9697,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9562,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9865,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.964,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9738,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9735,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9616,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.9679,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698225454888516e-05,
"loss": 3.9591,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9582,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.957,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9771,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9563,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694035756894003e-05,
"loss": 3.956,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9433,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9573,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.968,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.9712,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689842783138743e-05,
"loss": 3.9582,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9684,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9749,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9588,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9495,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856530851442285e-05,
"loss": 3.9594,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9525,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9554,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831373008910725e-05,
"loss": 3.9485,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9599,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9655,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.9523,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9397,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678947602896559e-05,
"loss": 3.9464,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678109008145507e-05,
"loss": 3.9518,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9582,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9514,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9537,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9519,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9413,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673077439639194e-05,
"loss": 3.9402,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9458,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714035258978375e-05,
"loss": 3.9483,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9523,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9467,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9331,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.95,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9564,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9431,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9471,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.933,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.9404,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9488,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.924,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613420267655863e-05,
"loss": 3.9328,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9418,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9405,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9295,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9406,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657150690890699e-05,
"loss": 3.9261,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656312096139647e-05,
"loss": 3.9449,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655473501388595e-05,
"loss": 3.9307,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9314,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653797949766864e-05,
"loss": 3.9445,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652959355015812e-05,
"loss": 3.9429,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652122398145134e-05,
"loss": 3.9388,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.9288,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.65044520864303e-05,
"loss": 3.9328,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649606613891978e-05,
"loss": 3.9346,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.929,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647929424389874e-05,
"loss": 3.9321,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9236,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.9382,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454152780170906e-05,
"loss": 3.9279,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445766832660386e-05,
"loss": 3.9266,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437380885149866e-05,
"loss": 3.9194,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429011316443075e-05,
"loss": 3.9315,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420625368932555e-05,
"loss": 3.9176,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412239421422035e-05,
"loss": 3.9406,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640385347391152e-05,
"loss": 3.9364,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.9288,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.9134,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378695631379955e-05,
"loss": 3.9363,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9312,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.9351,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635357054645586e-05,
"loss": 3.92,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634518459894534e-05,
"loss": 3.9294,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633679865143482e-05,
"loss": 3.9322,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632841270392429e-05,
"loss": 3.9399,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.9218,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631165718770699e-05,
"loss": 3.9273,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303271240196475e-05,
"loss": 3.9243,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629488529268595e-05,
"loss": 3.9114,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628649934517543e-05,
"loss": 3.9331,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.9306,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9188,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.62613578814476e-05,
"loss": 3.9214,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625297193393708e-05,
"loss": 3.9157,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.951601982116699,
"eval_runtime": 310.1749,
"eval_samples_per_second": 1230.245,
"eval_steps_per_second": 38.446,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624458598642656e-05,
"loss": 3.9098,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623620003891604e-05,
"loss": 3.9035,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227830470209246e-05,
"loss": 3.9284,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219444522698726e-05,
"loss": 3.9124,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621105857518821e-05,
"loss": 3.9278,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620267262767769e-05,
"loss": 3.9082,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619428668016717e-05,
"loss": 3.9129,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618591711146038e-05,
"loss": 3.9006,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617753116394986e-05,
"loss": 3.9131,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616914521643934e-05,
"loss": 3.9109,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616075926892882e-05,
"loss": 3.9191,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615238970022203e-05,
"loss": 3.9175,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614402013151524e-05,
"loss": 3.9071,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613563418400472e-05,
"loss": 3.901,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.61272482364942e-05,
"loss": 3.9005,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611886228898368e-05,
"loss": 3.8934,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611047634147316e-05,
"loss": 3.9024,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610209039396265e-05,
"loss": 3.9,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609370444645213e-05,
"loss": 3.8959,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085318498941607e-05,
"loss": 3.9252,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076948930234816e-05,
"loss": 3.904,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068562982724296e-05,
"loss": 3.9047,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060177035213776e-05,
"loss": 3.9106,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051791087703256e-05,
"loss": 3.9134,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043405140192735e-05,
"loss": 3.8915,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035035571485945e-05,
"loss": 3.8981,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026649623975425e-05,
"loss": 3.9079,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018263676464904e-05,
"loss": 3.9029,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009877728954384e-05,
"loss": 3.8874,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001491781443864e-05,
"loss": 3.8861,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599312221273708e-05,
"loss": 3.9057,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598473626522656e-05,
"loss": 3.9075,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597635031771604e-05,
"loss": 3.9003,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596796437020552e-05,
"loss": 3.9,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595959480149873e-05,
"loss": 3.8955,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595120885398821e-05,
"loss": 3.8983,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594282290647769e-05,
"loss": 3.8839,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593443695896717e-05,
"loss": 3.8997,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592606739026038e-05,
"loss": 3.8775,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591768144274986e-05,
"loss": 3.8911,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590929549523934e-05,
"loss": 3.8853,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590090954772882e-05,
"loss": 3.9046,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.58925236002183e-05,
"loss": 3.8933,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884154031511514e-05,
"loss": 3.8889,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875768084000994e-05,
"loss": 3.8933,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867382136490474e-05,
"loss": 3.8948,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858996188979954e-05,
"loss": 3.8978,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585061024146943e-05,
"loss": 3.871,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584225705156637e-05,
"loss": 3.8849,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583387110405585e-05,
"loss": 3.8968,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582548515654533e-05,
"loss": 3.8937,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581709920903481e-05,
"loss": 3.8822,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580871326152429e-05,
"loss": 3.8786,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580032731401377e-05,
"loss": 3.8794,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579194136650325e-05,
"loss": 3.8683,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578355541899273e-05,
"loss": 3.8934,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577516947148221e-05,
"loss": 3.8732,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576679990277543e-05,
"loss": 3.8868,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.57584139552649e-05,
"loss": 3.8863,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.575002800775438e-05,
"loss": 3.8711,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574164206024386e-05,
"loss": 3.8774,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733272491537076e-05,
"loss": 3.8721,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572488654402655e-05,
"loss": 3.869,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571650059651603e-05,
"loss": 3.8758,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570811464900551e-05,
"loss": 3.8853,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699745080298725e-05,
"loss": 3.87,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691359132788205e-05,
"loss": 3.8698,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682973185277685e-05,
"loss": 3.8592,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674587237767165e-05,
"loss": 3.8699,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666217669060374e-05,
"loss": 3.8787,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657831721549854e-05,
"loss": 3.8907,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649445774039334e-05,
"loss": 3.8698,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641059826528814e-05,
"loss": 3.8831,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632673879018294e-05,
"loss": 3.8861,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.56243043103115e-05,
"loss": 3.8822,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561591836280098e-05,
"loss": 3.8606,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560753241529046e-05,
"loss": 3.88,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559914646777994e-05,
"loss": 3.8726,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559077689907316e-05,
"loss": 3.8655,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558239095156264e-05,
"loss": 3.8729,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557400500405212e-05,
"loss": 3.8736,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.55656190565416e-05,
"loss": 3.8817,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555724948783481e-05,
"loss": 3.8689,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554886354032429e-05,
"loss": 3.8562,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554047759281377e-05,
"loss": 3.8662,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553209164530325e-05,
"loss": 3.8661,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552372207659646e-05,
"loss": 3.8748,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551533612908594e-05,
"loss": 3.8729,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550695018157542e-05,
"loss": 3.8679,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.54985642340649e-05,
"loss": 3.8725,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549019466535811e-05,
"loss": 3.8576,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548180871784759e-05,
"loss": 3.8585,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547342277033707e-05,
"loss": 3.8639,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546503682282655e-05,
"loss": 3.8682,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545666725411976e-05,
"loss": 3.87,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544828130660924e-05,
"loss": 3.8748,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543989535909872e-05,
"loss": 3.8485,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.54315094115882e-05,
"loss": 3.8721,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542313984288141e-05,
"loss": 3.8751,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541475389537089e-05,
"loss": 3.8662,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540636794786037e-05,
"loss": 3.8639,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539798200034985e-05,
"loss": 3.8535,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389612431643066e-05,
"loss": 3.8624,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381226484132546e-05,
"loss": 3.8659,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372840536622026e-05,
"loss": 3.8471,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364454589111506e-05,
"loss": 3.8576,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356085020404715e-05,
"loss": 3.8596,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347699072894195e-05,
"loss": 3.8645,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339329504187404e-05,
"loss": 3.8465,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330943556676884e-05,
"loss": 3.8689,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322557609166364e-05,
"loss": 3.8441,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314171661655844e-05,
"loss": 3.8691,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305785714145324e-05,
"loss": 3.8569,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297399766634804e-05,
"loss": 3.8504,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5289013819124284e-05,
"loss": 3.8678,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528062787161377e-05,
"loss": 3.8674,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527227468171071e-05,
"loss": 3.8596,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526388873420019e-05,
"loss": 3.8537,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525550278668967e-05,
"loss": 3.8578,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524711683917915e-05,
"loss": 3.858,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523873089166863e-05,
"loss": 3.8481,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523034494415811e-05,
"loss": 3.8556,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522195899664759e-05,
"loss": 3.8543,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521357304913707e-05,
"loss": 3.8591,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520520348043028e-05,
"loss": 3.8548,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519681753291976e-05,
"loss": 3.8547,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.8389,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180045637898725e-05,
"loss": 3.8563,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171676069191934e-05,
"loss": 3.8482,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163290121681414e-05,
"loss": 3.8629,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.861,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8567,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513814865795358e-05,
"loss": 3.8406,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512976271044306e-05,
"loss": 3.8601,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512137676293254e-05,
"loss": 3.8554,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511299081542202e-05,
"loss": 3.8635,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510462124671523e-05,
"loss": 3.8432,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509623529920471e-05,
"loss": 3.859,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508786573049793e-05,
"loss": 3.8613,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507947978298741e-05,
"loss": 3.8669,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507109383547689e-05,
"loss": 3.8436,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506270788796637e-05,
"loss": 3.8554,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505432194045585e-05,
"loss": 3.853,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504593599294533e-05,
"loss": 3.8435,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.50375500454348e-05,
"loss": 3.8548,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502916409792428e-05,
"loss": 3.8591,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020794529217496e-05,
"loss": 3.8492,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012408581706976e-05,
"loss": 3.8468,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500402263419645e-05,
"loss": 3.8486,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.910466432571411,
"eval_runtime": 306.1837,
"eval_samples_per_second": 1246.281,
"eval_steps_per_second": 38.947,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499563668668593e-05,
"loss": 3.8283,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987250739175416e-05,
"loss": 3.8344,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978864791664896e-05,
"loss": 3.8528,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970478844154376e-05,
"loss": 3.8461,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962092896643856e-05,
"loss": 3.8591,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953706949133336e-05,
"loss": 3.8393,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945321001622816e-05,
"loss": 3.8444,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936935054112296e-05,
"loss": 3.8264,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928565485405505e-05,
"loss": 3.8443,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920179537894985e-05,
"loss": 3.8434,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911793590384465e-05,
"loss": 3.8437,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903407642873945e-05,
"loss": 3.8495,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489505445297088e-05,
"loss": 3.8354,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488666850546037e-05,
"loss": 3.8364,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487828255794985e-05,
"loss": 3.8301,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486989661043933e-05,
"loss": 3.8251,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486151066292881e-05,
"loss": 3.8343,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485312471541829e-05,
"loss": 3.8324,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484473876790777e-05,
"loss": 3.8303,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483635282039725e-05,
"loss": 3.8524,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482798325169046e-05,
"loss": 3.836,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481959730417994e-05,
"loss": 3.8348,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481121135666942e-05,
"loss": 3.8436,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.48028254091589e-05,
"loss": 3.8455,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479445584045211e-05,
"loss": 3.8278,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478606989294159e-05,
"loss": 3.8339,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477768394543107e-05,
"loss": 3.8376,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476929799792055e-05,
"loss": 3.8344,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476092842921376e-05,
"loss": 3.8199,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475254248170324e-05,
"loss": 3.8202,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474415653419272e-05,
"loss": 3.8384,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47357705866822e-05,
"loss": 3.8404,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472740101797541e-05,
"loss": 3.835,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471901507046489e-05,
"loss": 3.8362,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471062912295437e-05,
"loss": 3.8278,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470224317544385e-05,
"loss": 3.8353,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469387360673706e-05,
"loss": 3.8211,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468548765922654e-05,
"loss": 3.8308,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467710171171602e-05,
"loss": 3.8126,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.46687157642055e-05,
"loss": 3.8239,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466034619549872e-05,
"loss": 3.8215,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.46519602479882e-05,
"loss": 3.8404,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464357430047768e-05,
"loss": 3.8284,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463518835296716e-05,
"loss": 3.8254,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626818784260366e-05,
"loss": 3.8289,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618432836749846e-05,
"loss": 3.8306,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610046889239326e-05,
"loss": 3.8328,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601660941728806e-05,
"loss": 3.8116,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593291373022015e-05,
"loss": 3.8186,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584905425511495e-05,
"loss": 3.8333,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576519478000975e-05,
"loss": 3.8287,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568133530490455e-05,
"loss": 3.8184,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455976396178367e-05,
"loss": 3.8137,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455137801427315e-05,
"loss": 3.8203,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454299206676263e-05,
"loss": 3.8082,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453460611925211e-05,
"loss": 3.8272,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452623655054532e-05,
"loss": 3.8114,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.45178506030348e-05,
"loss": 3.8217,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450946465552428e-05,
"loss": 3.8205,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450107870801376e-05,
"loss": 3.8144,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449270913930697e-05,
"loss": 3.8097,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448432319179645e-05,
"loss": 3.8137,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447593724428593e-05,
"loss": 3.8058,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446755129677541e-05,
"loss": 3.8137,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459181728068624e-05,
"loss": 3.8218,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450795780558104e-05,
"loss": 3.8097,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442409833047584e-05,
"loss": 3.8099,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443402388553706e-05,
"loss": 3.7979,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442565431683027e-05,
"loss": 3.8047,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441726836931975e-05,
"loss": 3.8184,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440888242180923e-05,
"loss": 3.8248,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400496474298706e-05,
"loss": 3.8124,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439212690559192e-05,
"loss": 3.8211,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.43837409580814e-05,
"loss": 3.8261,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437535501057088e-05,
"loss": 3.8205,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436696906306036e-05,
"loss": 3.8003,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435859949435358e-05,
"loss": 3.8179,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435021354684306e-05,
"loss": 3.8118,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434182759933253e-05,
"loss": 3.8049,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433344165182201e-05,
"loss": 3.8089,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432507208311523e-05,
"loss": 3.8155,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431668613560471e-05,
"loss": 3.8236,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430830018809418e-05,
"loss": 3.809,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429991424058366e-05,
"loss": 3.7927,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291544671876876e-05,
"loss": 3.8067,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283158724366356e-05,
"loss": 3.8079,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274772776855836e-05,
"loss": 3.8104,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266386829345316e-05,
"loss": 3.8123,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425801726063853e-05,
"loss": 3.8103,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249631313128005e-05,
"loss": 3.8127,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241245365617485e-05,
"loss": 3.8018,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.42328757969107e-05,
"loss": 3.7974,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422448984940018e-05,
"loss": 3.804,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216103901889654e-05,
"loss": 3.8125,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207717954379134e-05,
"loss": 3.8114,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419934838567235e-05,
"loss": 3.8158,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419096243816182e-05,
"loss": 3.7947,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418257649065131e-05,
"loss": 3.809,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417419054314079e-05,
"loss": 3.814,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165820974434005e-05,
"loss": 3.8112,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415743502692348e-05,
"loss": 3.8046,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414904907941296e-05,
"loss": 3.8003,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414066313190244e-05,
"loss": 3.8029,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132293563195654e-05,
"loss": 3.8097,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412390761568513e-05,
"loss": 3.7865,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411552166817461e-05,
"loss": 3.802,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410713572066409e-05,
"loss": 3.8008,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098766151957296e-05,
"loss": 3.8062,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409039658325051e-05,
"loss": 3.7896,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408201063573999e-05,
"loss": 3.8083,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407362468822948e-05,
"loss": 3.7975,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406523874071895e-05,
"loss": 3.8071,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405685279320843e-05,
"loss": 3.7988,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404846684569791e-05,
"loss": 3.7938,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404008089818739e-05,
"loss": 3.8098,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403169495067687e-05,
"loss": 3.8127,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402334176077382e-05,
"loss": 3.8037,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.40149558132633e-05,
"loss": 3.7947,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400656986575277e-05,
"loss": 3.8024,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399818391824225e-05,
"loss": 3.8028,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398979797073173e-05,
"loss": 3.7901,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398141202322122e-05,
"loss": 3.7998,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.39730260757107e-05,
"loss": 3.7969,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396464012820018e-05,
"loss": 3.8014,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956270559493386e-05,
"loss": 3.7969,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947884611982866e-05,
"loss": 3.8012,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939498664472346e-05,
"loss": 3.7854,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3931112716961826e-05,
"loss": 3.7992,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922743148255035e-05,
"loss": 3.7951,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914357200744515e-05,
"loss": 3.8072,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905971253233995e-05,
"loss": 3.7977,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897585305723475e-05,
"loss": 3.8051,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889215737016684e-05,
"loss": 3.7865,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388082978950617e-05,
"loss": 3.8059,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387244384199565e-05,
"loss": 3.8026,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386405789448513e-05,
"loss": 3.8058,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385568832577834e-05,
"loss": 3.7879,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384730237826782e-05,
"loss": 3.8044,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383893280956103e-05,
"loss": 3.8032,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383054686205051e-05,
"loss": 3.8174,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382216091453999e-05,
"loss": 3.7885,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381377496702947e-05,
"loss": 3.7999,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380538901951895e-05,
"loss": 3.7974,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379700307200843e-05,
"loss": 3.7883,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378861712449791e-05,
"loss": 3.8023,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378023117698739e-05,
"loss": 3.8038,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771861608280604e-05,
"loss": 3.7981,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763475660770084e-05,
"loss": 3.7889,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3755089713259564e-05,
"loss": 3.7978,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.885854959487915,
"eval_runtime": 305.8448,
"eval_samples_per_second": 1247.662,
"eval_steps_per_second": 38.99,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746703765749044e-05,
"loss": 3.7852,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373833419704225e-05,
"loss": 3.7776,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372994824953173e-05,
"loss": 3.7987,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372156230202121e-05,
"loss": 3.794,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371317635451069e-05,
"loss": 3.7999,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.37048067858039e-05,
"loss": 3.7891,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369642083829338e-05,
"loss": 3.7874,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368803489078286e-05,
"loss": 3.778,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367964894327234e-05,
"loss": 3.7902,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367127937456556e-05,
"loss": 3.7908,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366289342705504e-05,
"loss": 3.7903,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365450747954452e-05,
"loss": 3.7963,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364613791083773e-05,
"loss": 3.7849,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363775196332721e-05,
"loss": 3.7844,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.3629366015816687e-05,
"loss": 3.7809,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3620980068306167e-05,
"loss": 3.7724,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612594120795647e-05,
"loss": 3.7842,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.3604208173285126e-05,
"loss": 3.7793,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.3595822225774606e-05,
"loss": 3.7751,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358743627826408e-05,
"loss": 3.7971,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3579066709557295e-05,
"loss": 3.7883,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.3570680762046775e-05,
"loss": 3.7872,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.3562294814536255e-05,
"loss": 3.791,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.3553908867025735e-05,
"loss": 3.7955,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354553929831895e-05,
"loss": 3.7718,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353715335080843e-05,
"loss": 3.7831,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.3528767403297904e-05,
"loss": 3.7893,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352039783459112e-05,
"loss": 3.7785,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.35120118870806e-05,
"loss": 3.7714,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350362593957008e-05,
"loss": 3.7687,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.349523999205955e-05,
"loss": 3.7878,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348687042335277e-05,
"loss": 3.788,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347848447584225e-05,
"loss": 3.7847,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.347009852833173e-05,
"loss": 3.7876,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346171258082121e-05,
"loss": 3.778,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345332663331069e-05,
"loss": 3.7821,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344494068580017e-05,
"loss": 3.774,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343655473828965e-05,
"loss": 3.7811,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342816879077913e-05,
"loss": 3.7641,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341979922207234e-05,
"loss": 3.771,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341141327456182e-05,
"loss": 3.7723,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.34030273270513e-05,
"loss": 3.7897,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339465775834451e-05,
"loss": 3.7798,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338627181083399e-05,
"loss": 3.7754,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337788586332347e-05,
"loss": 3.7831,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336949991581295e-05,
"loss": 3.7766,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336113034710616e-05,
"loss": 3.7831,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335274439959564e-05,
"loss": 3.767,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334435845208512e-05,
"loss": 3.7654,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.33359725045746e-05,
"loss": 3.782,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332760293586781e-05,
"loss": 3.779,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331921698835729e-05,
"loss": 3.7684,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331083104084677e-05,
"loss": 3.7687,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330244509333625e-05,
"loss": 3.7715,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329407552462946e-05,
"loss": 3.7556,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328568957711894e-05,
"loss": 3.7798,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327730362960842e-05,
"loss": 3.7651,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.32689176820979e-05,
"loss": 3.7694,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.3260548113391116e-05,
"loss": 3.7768,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.3252162165880596e-05,
"loss": 3.7658,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.3243776218370076e-05,
"loss": 3.7635,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.3235390270859556e-05,
"loss": 3.7659,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.3227020702152765e-05,
"loss": 3.7595,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.3218634754642245e-05,
"loss": 3.7622,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.3210248807131725e-05,
"loss": 3.7743,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.3201862859621205e-05,
"loss": 3.7659,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.3193493290914414e-05,
"loss": 3.7593,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3185107343403894e-05,
"loss": 3.7547,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.3176721395893374e-05,
"loss": 3.7545,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3168335448382854e-05,
"loss": 3.7656,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315996587967607e-05,
"loss": 3.7754,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315157993216555e-05,
"loss": 3.7675,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314319398465503e-05,
"loss": 3.7738,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313480803714451e-05,
"loss": 3.7763,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312643846843772e-05,
"loss": 3.7791,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.31180525209272e-05,
"loss": 3.7518,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310966657341668e-05,
"loss": 3.7688,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310128062590616e-05,
"loss": 3.7679,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309291105719937e-05,
"loss": 3.7534,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308452510968885e-05,
"loss": 3.7671,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307613916217833e-05,
"loss": 3.7654,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306775321466781e-05,
"loss": 3.7754,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.3059383645961024e-05,
"loss": 3.7631,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3050997698450504e-05,
"loss": 3.7469,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042611750939984e-05,
"loss": 3.7602,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3034225803429464e-05,
"loss": 3.761,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.302585623472267e-05,
"loss": 3.7676,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301747028721215e-05,
"loss": 3.7617,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300908433970163e-05,
"loss": 3.7666,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300069839219111e-05,
"loss": 3.765,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299232882348432e-05,
"loss": 3.7573,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.29839428759738e-05,
"loss": 3.7486,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297555692846328e-05,
"loss": 3.7584,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296717098095276e-05,
"loss": 3.7684,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295880141224598e-05,
"loss": 3.7635,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295041546473546e-05,
"loss": 3.7675,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294202951722494e-05,
"loss": 3.7521,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293364356971442e-05,
"loss": 3.7635,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.2925274001007626e-05,
"loss": 3.7675,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.2916888053497106e-05,
"loss": 3.767,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.2908502105986586e-05,
"loss": 3.7575,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.2900116158476066e-05,
"loss": 3.7569,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.2891746589769275e-05,
"loss": 3.7571,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.2883360642258755e-05,
"loss": 3.7641,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.2874974694748235e-05,
"loss": 3.74,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286660512604145e-05,
"loss": 3.757,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285821917853093e-05,
"loss": 3.7506,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284983323102041e-05,
"loss": 3.764,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284146366231362e-05,
"loss": 3.7444,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.28330777148031e-05,
"loss": 3.769,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282469176729258e-05,
"loss": 3.7516,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281630581978206e-05,
"loss": 3.7626,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280791987227154e-05,
"loss": 3.753,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279953392476102e-05,
"loss": 3.7513,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.27911479772505e-05,
"loss": 3.7609,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278276202973998e-05,
"loss": 3.7698,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277440883983692e-05,
"loss": 3.759,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.2766022892326405e-05,
"loss": 3.7482,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.2757636944815885e-05,
"loss": 3.757,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.2749250997305365e-05,
"loss": 3.7595,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.2740865049794845e-05,
"loss": 3.748,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.2732479102284325e-05,
"loss": 3.7581,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.2724093154773805e-05,
"loss": 3.7473,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.2715707207263285e-05,
"loss": 3.7558,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.2707337638556494e-05,
"loss": 3.7562,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698951691045974e-05,
"loss": 3.7605,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.2690565743535454e-05,
"loss": 3.7379,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268217979602493e-05,
"loss": 3.7559,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267381022731814e-05,
"loss": 3.7494,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266542427980762e-05,
"loss": 3.7635,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.26570383322971e-05,
"loss": 3.7561,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.264865238478658e-05,
"loss": 3.7612,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.26402828160798e-05,
"loss": 3.7413,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.263189686856928e-05,
"loss": 3.7613,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262351092105876e-05,
"loss": 3.7594,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261512497354823e-05,
"loss": 3.7599,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260675540484145e-05,
"loss": 3.7491,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259836945733093e-05,
"loss": 3.7582,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.25899835098204e-05,
"loss": 3.7615,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258159756230988e-05,
"loss": 3.7707,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.2573244372406825e-05,
"loss": 3.7467,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256485842489631e-05,
"loss": 3.758,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255647247738579e-05,
"loss": 3.7551,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254808652987527e-05,
"loss": 3.745,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253970058236475e-05,
"loss": 3.7602,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253131463485423e-05,
"loss": 3.7565,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.2522928687343705e-05,
"loss": 3.7612,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.2514542739833185e-05,
"loss": 3.7447,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.25061731711264e-05,
"loss": 3.7536,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.869858503341675,
"eval_runtime": 310.6177,
"eval_samples_per_second": 1228.491,
"eval_steps_per_second": 38.391,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.2497787223615874e-05,
"loss": 3.7439,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.2489401276105354e-05,
"loss": 3.7306,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.2481015328594834e-05,
"loss": 3.7564,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.2472629381084314e-05,
"loss": 3.7523,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.2464243433573794e-05,
"loss": 3.7592,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245585748606328e-05,
"loss": 3.7486,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244747153855276e-05,
"loss": 3.7392,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243908559104224e-05,
"loss": 3.7394,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243071602233545e-05,
"loss": 3.7465,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242233007482493e-05,
"loss": 3.747,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241394412731441e-05,
"loss": 3.7503,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240555817980389e-05,
"loss": 3.755,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239720498990083e-05,
"loss": 3.7445,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238881904239031e-05,
"loss": 3.7389,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238043309487979e-05,
"loss": 3.7429,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237204714736927e-05,
"loss": 3.7283,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236366119985875e-05,
"loss": 3.7413,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.2355275252348234e-05,
"loss": 3.7392,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.2346889304837714e-05,
"loss": 3.7354,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.2338503357327194e-05,
"loss": 3.7565,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.23301337886204e-05,
"loss": 3.747,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232174784110988e-05,
"loss": 3.7468,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231336189359936e-05,
"loss": 3.7472,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230499232489257e-05,
"loss": 3.7524,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.229660637738205e-05,
"loss": 3.7319,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.228822042987153e-05,
"loss": 3.7452,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.227983448236101e-05,
"loss": 3.7425,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227144853485049e-05,
"loss": 3.7374,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226306258733997e-05,
"loss": 3.7336,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.225467663982945e-05,
"loss": 3.7251,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.224629069231893e-05,
"loss": 3.7491,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223793750241588e-05,
"loss": 3.7462,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222955155490536e-05,
"loss": 3.7434,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222116560739484e-05,
"loss": 3.7474,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221277965988432e-05,
"loss": 3.7364,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.22043937123738e-05,
"loss": 3.7417,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219600776486328e-05,
"loss": 3.7363,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218762181735276e-05,
"loss": 3.7347,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.2179252248645966e-05,
"loss": 3.7252,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.2170866301135446e-05,
"loss": 3.7309,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.2162480353624926e-05,
"loss": 3.7338,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.2154094406114406e-05,
"loss": 3.7494,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214572483740762e-05,
"loss": 3.7361,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.21373388898971e-05,
"loss": 3.7338,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212895294238658e-05,
"loss": 3.7461,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212056699487606e-05,
"loss": 3.7354,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211219742616927e-05,
"loss": 3.7432,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.210381147865875e-05,
"loss": 3.7285,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209542553114823e-05,
"loss": 3.7205,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208703958363771e-05,
"loss": 3.742,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.2078653636127184e-05,
"loss": 3.7387,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070267688616664e-05,
"loss": 3.7338,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.206189811990988e-05,
"loss": 3.7264,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.205351217239936e-05,
"loss": 3.7335,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204512622488884e-05,
"loss": 3.7128,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203674027737832e-05,
"loss": 3.7378,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.20283543298678e-05,
"loss": 3.728,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201996838235728e-05,
"loss": 3.7266,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201158243484676e-05,
"loss": 3.7391,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.2003229244943704e-05,
"loss": 3.7252,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.1994843297433184e-05,
"loss": 3.7223,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198645734992266e-05,
"loss": 3.7302,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197807140241214e-05,
"loss": 3.718,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196968545490162e-05,
"loss": 3.725,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196131588619483e-05,
"loss": 3.7327,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195292993868431e-05,
"loss": 3.7272,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194454399117379e-05,
"loss": 3.72,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193615804366327e-05,
"loss": 3.7174,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192777209615275e-05,
"loss": 3.7126,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191938614864223e-05,
"loss": 3.7254,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191100020113171e-05,
"loss": 3.7372,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.190263063242492e-05,
"loss": 3.728,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.18942446849144e-05,
"loss": 3.7366,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.188587511620761e-05,
"loss": 3.7338,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.187748916869709e-05,
"loss": 3.7414,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.186910322118657e-05,
"loss": 3.7167,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186071727367605e-05,
"loss": 3.7329,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.185233132616553e-05,
"loss": 3.7299,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.184394537865501e-05,
"loss": 3.7118,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.18355594311445e-05,
"loss": 3.7306,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182718986243771e-05,
"loss": 3.7297,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.1818803914927187e-05,
"loss": 3.7348,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.1810417967416667e-05,
"loss": 3.7259,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.1802032019906146e-05,
"loss": 3.7118,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.1793646072395626e-05,
"loss": 3.719,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.1785260124885106e-05,
"loss": 3.722,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776874177374586e-05,
"loss": 3.7285,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.1768504608667795e-05,
"loss": 3.7229,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.1760118661157275e-05,
"loss": 3.7302,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.1751732713646755e-05,
"loss": 3.7268,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.1743346766136235e-05,
"loss": 3.722,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173497719742945e-05,
"loss": 3.7113,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172659124991893e-05,
"loss": 3.7195,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171820530240841e-05,
"loss": 3.7327,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170981935489789e-05,
"loss": 3.7289,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.17014497861911e-05,
"loss": 3.7276,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169306383868058e-05,
"loss": 3.7135,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168467789117006e-05,
"loss": 3.7237,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167629194365954e-05,
"loss": 3.7303,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166792237495275e-05,
"loss": 3.7269,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165955280624596e-05,
"loss": 3.7224,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165116685873544e-05,
"loss": 3.7204,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164278091122492e-05,
"loss": 3.7214,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1634394963714405e-05,
"loss": 3.7256,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1626009016203885e-05,
"loss": 3.7047,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617623068693365e-05,
"loss": 3.7155,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1609237121182845e-05,
"loss": 3.7148,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.160085117367232e-05,
"loss": 3.7276,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159249798376926e-05,
"loss": 3.7098,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158411203625874e-05,
"loss": 3.7275,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157572608874822e-05,
"loss": 3.7158,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.15673401412377e-05,
"loss": 3.7224,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155895419372718e-05,
"loss": 3.7226,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155056824621666e-05,
"loss": 3.7118,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154218229870614e-05,
"loss": 3.7234,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153379635119562e-05,
"loss": 3.7327,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152544316129257e-05,
"loss": 3.7207,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151705721378205e-05,
"loss": 3.719,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150867126627153e-05,
"loss": 3.7119,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150028531876101e-05,
"loss": 3.7243,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149189937125049e-05,
"loss": 3.7166,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148351342373997e-05,
"loss": 3.7166,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1475143855033176e-05,
"loss": 3.709,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466757907522656e-05,
"loss": 3.7189,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1458371960012136e-05,
"loss": 3.7203,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.144998601250161e-05,
"loss": 3.7221,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441600064991096e-05,
"loss": 3.7031,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1433214117480576e-05,
"loss": 3.7227,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424828169970056e-05,
"loss": 3.7104,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1416458601263265e-05,
"loss": 3.7291,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1408072653752745e-05,
"loss": 3.7173,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399686706242225e-05,
"loss": 3.728,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.1391300758731705e-05,
"loss": 3.7051,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.1382914811221185e-05,
"loss": 3.7273,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.1374528863710665e-05,
"loss": 3.7217,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.1366159295003874e-05,
"loss": 3.7252,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.1357773347493354e-05,
"loss": 3.7077,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.1349387399982834e-05,
"loss": 3.7221,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.1341001452472314e-05,
"loss": 3.7259,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.1332615504961794e-05,
"loss": 3.7334,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132424593625501e-05,
"loss": 3.7132,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131585998874449e-05,
"loss": 3.7211,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130747404123397e-05,
"loss": 3.7221,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129908809372345e-05,
"loss": 3.7138,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129070214621293e-05,
"loss": 3.7203,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128233257750614e-05,
"loss": 3.7211,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127394662999562e-05,
"loss": 3.7223,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.12655606824851e-05,
"loss": 3.7118,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125717473497458e-05,
"loss": 3.7183,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.859259843826294,
"eval_runtime": 306.5299,
"eval_samples_per_second": 1244.874,
"eval_steps_per_second": 38.903,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124878878746406e-05,
"loss": 3.7126,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.124040283995354e-05,
"loss": 3.6957,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.123201689244302e-05,
"loss": 3.7179,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.122364732373623e-05,
"loss": 3.7183,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.1215261376225714e-05,
"loss": 3.7196,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.1206875428715194e-05,
"loss": 3.7141,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.1198489481204674e-05,
"loss": 3.707,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.1190103533694154e-05,
"loss": 3.7036,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.118171758618363e-05,
"loss": 3.7119,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117333163867311e-05,
"loss": 3.7091,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116496206996632e-05,
"loss": 3.7142,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.1156576122455796e-05,
"loss": 3.7196,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114820655374901e-05,
"loss": 3.7118,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113982060623849e-05,
"loss": 3.7059,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113143465872797e-05,
"loss": 3.7046,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112304871121745e-05,
"loss": 3.6904,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111466276370693e-05,
"loss": 3.7073,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110627681619641e-05,
"loss": 3.7053,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109789086868589e-05,
"loss": 3.7039,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108950492117537e-05,
"loss": 3.7166,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108111897366485e-05,
"loss": 3.7166,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.107273302615433e-05,
"loss": 3.7103,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.106434707864381e-05,
"loss": 3.712,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.105597750993702e-05,
"loss": 3.715,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.10475915624265e-05,
"loss": 3.6996,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.103920561491598e-05,
"loss": 3.7115,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.103081966740546e-05,
"loss": 3.7107,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102243371989494e-05,
"loss": 3.7039,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101406415118815e-05,
"loss": 3.6979,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.1005678203677637e-05,
"loss": 3.6964,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.0997292256167117e-05,
"loss": 3.7098,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.0988906308656597e-05,
"loss": 3.7151,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.0980520361146076e-05,
"loss": 3.7102,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.0972150792439286e-05,
"loss": 3.7121,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.0963764844928766e-05,
"loss": 3.6978,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.0955378897418245e-05,
"loss": 3.709,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.0946992949907725e-05,
"loss": 3.7089,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.0938623381200935e-05,
"loss": 3.6966,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.0930237433690414e-05,
"loss": 3.6966,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.0921851486179894e-05,
"loss": 3.6954,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.0913465538669374e-05,
"loss": 3.6981,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.0905079591158854e-05,
"loss": 3.7162,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.0896693643648334e-05,
"loss": 3.703,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088832407494155e-05,
"loss": 3.6969,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.087993812743103e-05,
"loss": 3.7115,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087155217992051e-05,
"loss": 3.7044,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086316623240999e-05,
"loss": 3.7073,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085478028489946e-05,
"loss": 3.6947,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084639433738894e-05,
"loss": 3.6859,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.083800838987842e-05,
"loss": 3.7138,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.08296224423679e-05,
"loss": 3.7018,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082125287366111e-05,
"loss": 3.6998,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081288330495433e-05,
"loss": 3.6976,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080449735744381e-05,
"loss": 3.6917,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079611140993329e-05,
"loss": 3.6861,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078772546242277e-05,
"loss": 3.7008,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077933951491225e-05,
"loss": 3.6965,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.0770969946205464e-05,
"loss": 3.6972,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.076258399869494e-05,
"loss": 3.7041,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075419805118442e-05,
"loss": 3.6934,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.07458121036739e-05,
"loss": 3.6888,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.0737442534967106e-05,
"loss": 3.7006,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.0729056587456586e-05,
"loss": 3.6828,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.0720670639946066e-05,
"loss": 3.6918,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.0712284692435546e-05,
"loss": 3.6988,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.0703898744925026e-05,
"loss": 3.6958,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.0695512797414506e-05,
"loss": 3.687,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.068712684990399e-05,
"loss": 3.6865,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067874090239347e-05,
"loss": 3.6772,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.067037133368668e-05,
"loss": 3.6946,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066198538617616e-05,
"loss": 3.7027,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.065361581746937e-05,
"loss": 3.6977,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064522986995885e-05,
"loss": 3.699,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.063684392244833e-05,
"loss": 3.7016,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.062845797493781e-05,
"loss": 3.7108,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.062007202742729e-05,
"loss": 3.6813,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.061168607991677e-05,
"loss": 3.7022,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060330013240625e-05,
"loss": 3.6981,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.059493056369946e-05,
"loss": 3.675,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.0586544616188946e-05,
"loss": 3.7027,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.0578158668678426e-05,
"loss": 3.6918,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.0569772721167906e-05,
"loss": 3.7041,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.0561403152461115e-05,
"loss": 3.6963,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.0553017204950595e-05,
"loss": 3.6793,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.0544631257440075e-05,
"loss": 3.6842,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.0536245309929555e-05,
"loss": 3.6931,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.0527859362419035e-05,
"loss": 3.694,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.0519473414908515e-05,
"loss": 3.6917,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.0511087467397995e-05,
"loss": 3.6978,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.050270151988747e-05,
"loss": 3.6924,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.0494331951180684e-05,
"loss": 3.6889,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.0485946003670164e-05,
"loss": 3.686,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.0477560056159644e-05,
"loss": 3.6839,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.0469174108649124e-05,
"loss": 3.6997,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046080453994234e-05,
"loss": 3.6959,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045243497123555e-05,
"loss": 3.701,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044404902372503e-05,
"loss": 3.6785,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043566307621451e-05,
"loss": 3.6925,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042727712870399e-05,
"loss": 3.6975,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041889118119347e-05,
"loss": 3.697,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.041052161248668e-05,
"loss": 3.6904,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040213566497616e-05,
"loss": 3.6863,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039374971746564e-05,
"loss": 3.6897,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038536376995512e-05,
"loss": 3.6932,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.03769778224446e-05,
"loss": 3.6721,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036859187493408e-05,
"loss": 3.6899,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.036020592742356e-05,
"loss": 3.6796,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0351836358716766e-05,
"loss": 3.6983,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0343450411206246e-05,
"loss": 3.6795,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.0335064463695726e-05,
"loss": 3.6906,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.0326678516185206e-05,
"loss": 3.6876,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.0318292568674686e-05,
"loss": 3.695,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.0309906621164166e-05,
"loss": 3.6891,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.0301537052457375e-05,
"loss": 3.6787,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.0293151104946855e-05,
"loss": 3.6915,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.0284765157436335e-05,
"loss": 3.6995,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.0276379209925815e-05,
"loss": 3.6897,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.02679932624153e-05,
"loss": 3.6903,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025960731490478e-05,
"loss": 3.679,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025123774619799e-05,
"loss": 3.6909,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024285179868747e-05,
"loss": 3.6903,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023446585117695e-05,
"loss": 3.6808,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022607990366643e-05,
"loss": 3.684,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021769395615591e-05,
"loss": 3.6864,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020930800864539e-05,
"loss": 3.6911,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.020092206113487e-05,
"loss": 3.6924,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.019255249242808e-05,
"loss": 3.6728,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.018416654491756e-05,
"loss": 3.6922,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017578059740704e-05,
"loss": 3.6767,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.0167411028700256e-05,
"loss": 3.6966,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.0159025081189736e-05,
"loss": 3.6875,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.0150639133679216e-05,
"loss": 3.6963,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.0142253186168696e-05,
"loss": 3.6744,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.0133867238658175e-05,
"loss": 3.6982,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.0125497669951385e-05,
"loss": 3.6894,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.0117111722440865e-05,
"loss": 3.6931,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.0108725774930344e-05,
"loss": 3.6822,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.0100339827419824e-05,
"loss": 3.6861,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.0091953879909304e-05,
"loss": 3.6916,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008356793239878e-05,
"loss": 3.7067,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.0075198363691993e-05,
"loss": 3.6831,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006681241618147e-05,
"loss": 3.6892,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005842646867095e-05,
"loss": 3.6953,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.005004052116043e-05,
"loss": 3.6821,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004167095245365e-05,
"loss": 3.6837,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003328500494313e-05,
"loss": 3.6919,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.00248990574326e-05,
"loss": 3.6921,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001651310992208e-05,
"loss": 3.6824,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000812716241156e-05,
"loss": 3.6884,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 3.8526220321655273,
"eval_runtime": 352.6196,
"eval_samples_per_second": 1082.16,
"eval_steps_per_second": 33.818,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999974121490104e-05,
"loss": 3.6745,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999135526739052e-05,
"loss": 3.6697,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998296931988e-05,
"loss": 3.6835,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997458337236948e-05,
"loss": 3.686,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996619742485896e-05,
"loss": 3.6933,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995782785615218e-05,
"loss": 3.6805,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994944190864166e-05,
"loss": 3.6784,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994105596113114e-05,
"loss": 3.6751,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993267001362062e-05,
"loss": 3.6784,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.99242840661101e-05,
"loss": 3.6813,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991589811859958e-05,
"loss": 3.6842,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990752854989279e-05,
"loss": 3.686,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.9899158981185996e-05,
"loss": 3.6819,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890773033675476e-05,
"loss": 3.6789,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9882387086164956e-05,
"loss": 3.6772,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9874001138654436e-05,
"loss": 3.661,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.9865615191143916e-05,
"loss": 3.6742,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.9857229243633396e-05,
"loss": 3.6758,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848843296122876e-05,
"loss": 3.6758,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.9840457348612356e-05,
"loss": 3.6812,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983208777990557e-05,
"loss": 3.6879,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.982370183239505e-05,
"loss": 3.6815,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981531588488453e-05,
"loss": 3.6822,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980692993737401e-05,
"loss": 3.6842,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979854398986349e-05,
"loss": 3.6726,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.9790158042352964e-05,
"loss": 3.6822,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781772094842444e-05,
"loss": 3.6806,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.9773386147331924e-05,
"loss": 3.6751,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976503295742887e-05,
"loss": 3.6728,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975664700991835e-05,
"loss": 3.6648,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974826106240783e-05,
"loss": 3.6784,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973987511489731e-05,
"loss": 3.6878,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973148916738679e-05,
"loss": 3.6811,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.9723119598680005e-05,
"loss": 3.6777,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.9714733651169485e-05,
"loss": 3.6685,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.9706347703658965e-05,
"loss": 3.6823,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969796175614844e-05,
"loss": 3.6775,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.9689592187441654e-05,
"loss": 3.6715,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.9681206239931134e-05,
"loss": 3.6679,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.9672820292420614e-05,
"loss": 3.6637,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966443434491009e-05,
"loss": 3.6652,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.96560647762033e-05,
"loss": 3.6868,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964767882869278e-05,
"loss": 3.6737,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963929288118226e-05,
"loss": 3.6706,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.963090693367174e-05,
"loss": 3.6806,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962252098616122e-05,
"loss": 3.6736,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.96141350386507e-05,
"loss": 3.6817,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960574909114018e-05,
"loss": 3.6708,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959736314362966e-05,
"loss": 3.6499,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958899357492287e-05,
"loss": 3.6857,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.958060762741235e-05,
"loss": 3.6727,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957222167990183e-05,
"loss": 3.6763,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956385211119504e-05,
"loss": 3.6672,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955546616368452e-05,
"loss": 3.6614,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.9547080216174e-05,
"loss": 3.6608,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953869426866349e-05,
"loss": 3.6711,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.9530324699956696e-05,
"loss": 3.6677,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.9521938752446176e-05,
"loss": 3.6653,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.9513552804935656e-05,
"loss": 3.6788,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.9505166857425136e-05,
"loss": 3.6625,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.9496780909914616e-05,
"loss": 3.6581,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.9488411341207825e-05,
"loss": 3.6761,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.9480025393697305e-05,
"loss": 3.6534,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.9471639446186785e-05,
"loss": 3.6585,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.9463253498676265e-05,
"loss": 3.6735,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.9454867551165745e-05,
"loss": 3.6677,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.9446497982458954e-05,
"loss": 3.656,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.943811203494844e-05,
"loss": 3.6591,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942972608743792e-05,
"loss": 3.6516,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.94213401399274e-05,
"loss": 3.6645,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941295419241688e-05,
"loss": 3.6735,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940458462371009e-05,
"loss": 3.6663,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939619867619957e-05,
"loss": 3.6695,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938781272868905e-05,
"loss": 3.6761,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937942678117853e-05,
"loss": 3.6823,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937104083366801e-05,
"loss": 3.6543,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936267126496122e-05,
"loss": 3.676,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.93542853174507e-05,
"loss": 3.6661,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934589936994018e-05,
"loss": 3.6493,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933751342242966e-05,
"loss": 3.6721,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.9329143853722875e-05,
"loss": 3.6669,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.9320757906212355e-05,
"loss": 3.676,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.9312371958701835e-05,
"loss": 3.6666,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.9303986011191315e-05,
"loss": 3.6537,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.9295600063680794e-05,
"loss": 3.6546,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.9287214116170274e-05,
"loss": 3.6661,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.9278844547463484e-05,
"loss": 3.6644,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.9270458599952964e-05,
"loss": 3.6675,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.9262072652442443e-05,
"loss": 3.6664,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925368670493192e-05,
"loss": 3.6638,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.9245300757421397e-05,
"loss": 3.6652,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.9236914809910877e-05,
"loss": 3.656,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922854524120409e-05,
"loss": 3.6591,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.922015929369357e-05,
"loss": 3.6722,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.921177334618305e-05,
"loss": 3.6652,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.920338739867253e-05,
"loss": 3.6729,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.919501782996575e-05,
"loss": 3.6523,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.918663188245522e-05,
"loss": 3.6645,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.91782459349447e-05,
"loss": 3.6681,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916985998743418e-05,
"loss": 3.6662,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916149041872739e-05,
"loss": 3.6627,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915310447121687e-05,
"loss": 3.6615,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914471852370635e-05,
"loss": 3.6636,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913633257619583e-05,
"loss": 3.6638,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912794662868532e-05,
"loss": 3.6522,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.91195606811748e-05,
"loss": 3.6594,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.9111191112468006e-05,
"loss": 3.6541,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9102805164957486e-05,
"loss": 3.6705,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.9094419217446966e-05,
"loss": 3.6529,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.9086033269936446e-05,
"loss": 3.6617,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.9077663701229655e-05,
"loss": 3.657,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.9069277753719135e-05,
"loss": 3.6717,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060891806208615e-05,
"loss": 3.6602,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.9052505858698095e-05,
"loss": 3.6528,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.9044136289991304e-05,
"loss": 3.6662,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.9035750342480784e-05,
"loss": 3.6721,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9027364394970264e-05,
"loss": 3.664,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.901897844745975e-05,
"loss": 3.6612,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.901060887875296e-05,
"loss": 3.6527,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900222293124244e-05,
"loss": 3.6623,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899383698373192e-05,
"loss": 3.6622,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.89854510362214e-05,
"loss": 3.653,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897706508871088e-05,
"loss": 3.6546,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.896867914120036e-05,
"loss": 3.6623,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.896030957249357e-05,
"loss": 3.6646,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895192362498305e-05,
"loss": 3.6629,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.894353767747253e-05,
"loss": 3.6476,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.893515172996201e-05,
"loss": 3.663,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.892678216125522e-05,
"loss": 3.651,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8918396213744704e-05,
"loss": 3.6693,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8910010266234184e-05,
"loss": 3.6619,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.8901624318723664e-05,
"loss": 3.6696,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889325475001687e-05,
"loss": 3.6451,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888486880250635e-05,
"loss": 3.6706,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887648285499583e-05,
"loss": 3.6617,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886809690748531e-05,
"loss": 3.6665,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885971095997479e-05,
"loss": 3.6563,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.8851341391268e-05,
"loss": 3.6551,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884295544375748e-05,
"loss": 3.6642,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883456949624696e-05,
"loss": 3.683,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882618354873644e-05,
"loss": 3.6552,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881779760122592e-05,
"loss": 3.6636,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.88094116537154e-05,
"loss": 3.6692,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880104208500862e-05,
"loss": 3.6537,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.87926561374981e-05,
"loss": 3.6593,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878427018998758e-05,
"loss": 3.6634,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877588424247705e-05,
"loss": 3.6676,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876751467377027e-05,
"loss": 3.6598,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875912872625975e-05,
"loss": 3.6601,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.848252058029175,
"eval_runtime": 302.9762,
"eval_samples_per_second": 1259.475,
"eval_steps_per_second": 39.36,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875074277874923e-05,
"loss": 3.65,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.87423568312387e-05,
"loss": 3.6419,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873397088372818e-05,
"loss": 3.6576,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.8725601315021396e-05,
"loss": 3.6625,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8717215367510876e-05,
"loss": 3.666,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.8708829420000356e-05,
"loss": 3.6537,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.8700443472489836e-05,
"loss": 3.6563,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869207390378305e-05,
"loss": 3.6474,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.8683687956272525e-05,
"loss": 3.6493,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.8675302008762005e-05,
"loss": 3.6572,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.8666916061251485e-05,
"loss": 3.657,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.86585464925447e-05,
"loss": 3.6568,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.865017692383791e-05,
"loss": 3.6636,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.864179097632739e-05,
"loss": 3.6466,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.863340502881687e-05,
"loss": 3.6509,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.862501908130635e-05,
"loss": 3.6347,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.861663313379583e-05,
"loss": 3.6484,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.860824718628531e-05,
"loss": 3.6508,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.859986123877479e-05,
"loss": 3.6483,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859147529126427e-05,
"loss": 3.6572,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858310572255748e-05,
"loss": 3.6624,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857471977504696e-05,
"loss": 3.6571,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856633382753644e-05,
"loss": 3.6574,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855794788002592e-05,
"loss": 3.6531,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854957831131913e-05,
"loss": 3.6484,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854119236380861e-05,
"loss": 3.6567,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853280641629809e-05,
"loss": 3.6519,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852442046878757e-05,
"loss": 3.6545,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851605090008078e-05,
"loss": 3.6442,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850766495257026e-05,
"loss": 3.6422,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849927900505974e-05,
"loss": 3.6472,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.849089305754922e-05,
"loss": 3.6616,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.84825071100387e-05,
"loss": 3.6563,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847413754133191e-05,
"loss": 3.6541,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846575159382139e-05,
"loss": 3.6423,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845736564631087e-05,
"loss": 3.6526,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.844897969880035e-05,
"loss": 3.6572,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.844061013009356e-05,
"loss": 3.6458,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843222418258304e-05,
"loss": 3.6438,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842383823507252e-05,
"loss": 3.6365,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.8415452287562e-05,
"loss": 3.6414,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840708271885522e-05,
"loss": 3.6583,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.8398696771344697e-05,
"loss": 3.6513,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.8390310823834177e-05,
"loss": 3.6442,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.8381924876323656e-05,
"loss": 3.6549,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.8373538928813136e-05,
"loss": 3.6493,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.8365169360106346e-05,
"loss": 3.6543,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.8356783412595825e-05,
"loss": 3.6505,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.8348397465085305e-05,
"loss": 3.6216,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.8340011517574785e-05,
"loss": 3.6648,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.8331641948867994e-05,
"loss": 3.6432,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.8323256001357474e-05,
"loss": 3.6542,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.8314870053846954e-05,
"loss": 3.6372,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.8306484106336434e-05,
"loss": 3.6414,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829811453762965e-05,
"loss": 3.6337,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828972859011913e-05,
"loss": 3.6423,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828134264260861e-05,
"loss": 3.6435,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827295669509809e-05,
"loss": 3.6393,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.82645871263913e-05,
"loss": 3.6575,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825620117888078e-05,
"loss": 3.637,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824781523137026e-05,
"loss": 3.6334,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.823942928385974e-05,
"loss": 3.6512,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.823104333634922e-05,
"loss": 3.6318,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.822267376764243e-05,
"loss": 3.632,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.821428782013191e-05,
"loss": 3.6474,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.820590187262139e-05,
"loss": 3.6418,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8197515925110875e-05,
"loss": 3.6328,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.8189129977600355e-05,
"loss": 3.6304,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.8180760408893564e-05,
"loss": 3.6298,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.8172374461383044e-05,
"loss": 3.6394,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.8163988513872524e-05,
"loss": 3.6493,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.8155602566362004e-05,
"loss": 3.64,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814723299765521e-05,
"loss": 3.6466,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.813884705014469e-05,
"loss": 3.649,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.813046110263417e-05,
"loss": 3.6574,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812207515512365e-05,
"loss": 3.6286,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811370558641686e-05,
"loss": 3.6539,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810531963890634e-05,
"loss": 3.6375,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.809693369139583e-05,
"loss": 3.6256,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808854774388531e-05,
"loss": 3.6436,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.808017817517852e-05,
"loss": 3.6517,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.8071792227668e-05,
"loss": 3.6472,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806340628015748e-05,
"loss": 3.6476,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805502033264696e-05,
"loss": 3.6267,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.8046650763940166e-05,
"loss": 3.6282,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.8038264816429646e-05,
"loss": 3.6445,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.8029878868919126e-05,
"loss": 3.6378,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.80214929214086e-05,
"loss": 3.6409,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.8013123352701815e-05,
"loss": 3.6456,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.8004737405191295e-05,
"loss": 3.6399,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799635145768078e-05,
"loss": 3.638,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.7987965510170255e-05,
"loss": 3.6342,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.7979579562659735e-05,
"loss": 3.633,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797120999395295e-05,
"loss": 3.6475,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796282404644243e-05,
"loss": 3.6427,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.7954438098931904e-05,
"loss": 3.6466,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.7946052151421384e-05,
"loss": 3.6335,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.79376825827146e-05,
"loss": 3.6354,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792929663520407e-05,
"loss": 3.6459,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792091068769355e-05,
"loss": 3.6429,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791252474018303e-05,
"loss": 3.6399,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790415517147625e-05,
"loss": 3.6393,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789576922396573e-05,
"loss": 3.637,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788738327645521e-05,
"loss": 3.6327,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.787899732894469e-05,
"loss": 3.6351,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.787061138143417e-05,
"loss": 3.6326,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786224181272738e-05,
"loss": 3.6272,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785385586521686e-05,
"loss": 3.6484,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784546991770634e-05,
"loss": 3.6313,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783708397019582e-05,
"loss": 3.6355,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782871440148903e-05,
"loss": 3.6322,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.782032845397851e-05,
"loss": 3.6443,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781194250646799e-05,
"loss": 3.6382,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.7803556558957474e-05,
"loss": 3.6288,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.779518699025068e-05,
"loss": 3.6455,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778680104274016e-05,
"loss": 3.6452,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777841509522964e-05,
"loss": 3.6385,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.777002914771912e-05,
"loss": 3.6337,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776165957901233e-05,
"loss": 3.6343,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.775327363150181e-05,
"loss": 3.6349,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774488768399129e-05,
"loss": 3.6405,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773650173648077e-05,
"loss": 3.6292,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772811578897025e-05,
"loss": 3.6312,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771974622026346e-05,
"loss": 3.6378,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771136027275294e-05,
"loss": 3.6409,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770297432524243e-05,
"loss": 3.6373,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769458837773191e-05,
"loss": 3.6246,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.7686218809025116e-05,
"loss": 3.641,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.7677832861514596e-05,
"loss": 3.6256,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.7669446914004076e-05,
"loss": 3.6436,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.7661060966493556e-05,
"loss": 3.6375,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.7652691397786765e-05,
"loss": 3.6484,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.7644305450276245e-05,
"loss": 3.6192,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.7635919502765725e-05,
"loss": 3.6491,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.7627533555255205e-05,
"loss": 3.6361,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.7619163986548414e-05,
"loss": 3.6441,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.7610778039037894e-05,
"loss": 3.6356,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760239209152738e-05,
"loss": 3.6271,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759400614401686e-05,
"loss": 3.6447,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758563657531007e-05,
"loss": 3.6567,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.757725062779955e-05,
"loss": 3.6364,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.756886468028903e-05,
"loss": 3.639,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.756047873277851e-05,
"loss": 3.6442,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755210916407172e-05,
"loss": 3.6303,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.75437232165612e-05,
"loss": 3.6336,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.753533726905068e-05,
"loss": 3.643,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752695132154016e-05,
"loss": 3.6402,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751858175283337e-05,
"loss": 3.6394,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.751019580532285e-05,
"loss": 3.6344,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 3.846360921859741,
"eval_runtime": 303.2963,
"eval_samples_per_second": 1258.146,
"eval_steps_per_second": 39.318,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750180985781233e-05,
"loss": 3.6203,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.7493423910301815e-05,
"loss": 3.6188,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.7485037962791294e-05,
"loss": 3.6342,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.7476652015280774e-05,
"loss": 3.6409,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.7468282446573984e-05,
"loss": 3.6414,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.7459896499063463e-05,
"loss": 3.6326,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.7451510551552943e-05,
"loss": 3.6323,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744312460404242e-05,
"loss": 3.624,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743475503533563e-05,
"loss": 3.6298,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742636908782511e-05,
"loss": 3.6324,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741798314031459e-05,
"loss": 3.6317,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740959719280407e-05,
"loss": 3.6341,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740121124529355e-05,
"loss": 3.6431,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739284167658677e-05,
"loss": 3.6207,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738445572907625e-05,
"loss": 3.6315,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737606978156573e-05,
"loss": 3.6081,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736768383405521e-05,
"loss": 3.6262,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735931426534842e-05,
"loss": 3.6263,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.73509283178379e-05,
"loss": 3.6228,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734254237032738e-05,
"loss": 3.6319,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733415642281686e-05,
"loss": 3.6382,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.7325786854110066e-05,
"loss": 3.6347,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.7317400906599546e-05,
"loss": 3.6359,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.7309014959089026e-05,
"loss": 3.6292,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7300629011578506e-05,
"loss": 3.6284,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.729225944287172e-05,
"loss": 3.6331,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.72838734953612e-05,
"loss": 3.6297,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727548754785068e-05,
"loss": 3.6318,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.7267101600340155e-05,
"loss": 3.6209,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.7258715652829635e-05,
"loss": 3.6183,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.725034608412285e-05,
"loss": 3.6217,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724196013661233e-05,
"loss": 3.6395,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.7233574189101804e-05,
"loss": 3.6367,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.7225188241591284e-05,
"loss": 3.6262,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.72168186728845e-05,
"loss": 3.6236,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720843272537398e-05,
"loss": 3.6222,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.720004677786346e-05,
"loss": 3.6373,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719166083035294e-05,
"loss": 3.626,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718327488284242e-05,
"loss": 3.6222,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717490531413563e-05,
"loss": 3.6156,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716651936662511e-05,
"loss": 3.6203,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715813341911459e-05,
"loss": 3.6302,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.714974747160407e-05,
"loss": 3.629,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714137790289728e-05,
"loss": 3.6249,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713299195538676e-05,
"loss": 3.6318,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712460600787624e-05,
"loss": 3.6259,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711622006036572e-05,
"loss": 3.6311,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.71078341128552e-05,
"loss": 3.6279,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709946454414841e-05,
"loss": 3.5995,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709107859663789e-05,
"loss": 3.6391,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708269264912737e-05,
"loss": 3.6191,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707430670161685e-05,
"loss": 3.6339,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.706593713291006e-05,
"loss": 3.6207,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705755118539954e-05,
"loss": 3.6159,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.704916523788902e-05,
"loss": 3.6087,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.70407792903785e-05,
"loss": 3.6207,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703240972167171e-05,
"loss": 3.6199,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702402377416119e-05,
"loss": 3.6153,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.701563782665067e-05,
"loss": 3.6335,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.700725187914015e-05,
"loss": 3.6198,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699888231043337e-05,
"loss": 3.603,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.699049636292285e-05,
"loss": 3.6315,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698211041541233e-05,
"loss": 3.6103,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.697372446790181e-05,
"loss": 3.6089,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696533852039129e-05,
"loss": 3.6241,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.6956968951684496e-05,
"loss": 3.6203,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.6948583004173976e-05,
"loss": 3.6102,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.6940197056663456e-05,
"loss": 3.6069,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.6931827487956665e-05,
"loss": 3.6105,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.6923441540446145e-05,
"loss": 3.6174,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.6915055592935625e-05,
"loss": 3.6256,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.6906669645425105e-05,
"loss": 3.6196,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.6898283697914585e-05,
"loss": 3.6281,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.68899141292078e-05,
"loss": 3.6247,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688152818169728e-05,
"loss": 3.633,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.687314223418676e-05,
"loss": 3.6138,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686475628667624e-05,
"loss": 3.6261,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685637033916572e-05,
"loss": 3.615,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684800077045893e-05,
"loss": 3.607,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683961482294841e-05,
"loss": 3.6199,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.683122887543789e-05,
"loss": 3.6309,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682284292792737e-05,
"loss": 3.6228,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.681447335922058e-05,
"loss": 3.6291,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680608741171006e-05,
"loss": 3.5995,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.679770146419954e-05,
"loss": 3.6109,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678931551668902e-05,
"loss": 3.6174,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.6780945947982234e-05,
"loss": 3.62,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.6772560000471714e-05,
"loss": 3.6127,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.6764174052961194e-05,
"loss": 3.6249,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.6755788105450674e-05,
"loss": 3.6189,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.6747402157940154e-05,
"loss": 3.6219,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.673903258923336e-05,
"loss": 3.6075,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.673064664172284e-05,
"loss": 3.6114,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672226069421232e-05,
"loss": 3.6268,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.67138747467018e-05,
"loss": 3.6189,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670550517799501e-05,
"loss": 3.6262,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669711923048449e-05,
"loss": 3.6136,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668873328297397e-05,
"loss": 3.6093,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.668034733546345e-05,
"loss": 3.6239,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667197776675667e-05,
"loss": 3.6221,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666359181924615e-05,
"loss": 3.6193,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.665520587173563e-05,
"loss": 3.6163,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664681992422511e-05,
"loss": 3.6131,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.663843397671459e-05,
"loss": 3.6116,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.66300644080078e-05,
"loss": 3.6155,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662167846049728e-05,
"loss": 3.6088,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661329251298676e-05,
"loss": 3.609,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.660490656547623e-05,
"loss": 3.6195,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.6596536996769446e-05,
"loss": 3.6176,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.6588151049258926e-05,
"loss": 3.6084,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.6579765101748406e-05,
"loss": 3.6141,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.6571379154237886e-05,
"loss": 3.6174,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.6562993206727366e-05,
"loss": 3.6181,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655462363802058e-05,
"loss": 3.6068,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654623769051006e-05,
"loss": 3.623,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.6537851742999535e-05,
"loss": 3.6264,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.6529465795489015e-05,
"loss": 3.6224,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652109622678223e-05,
"loss": 3.61,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.6512710279271704e-05,
"loss": 3.6137,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.6504324331761184e-05,
"loss": 3.6147,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.6495938384250663e-05,
"loss": 3.6226,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648756881554388e-05,
"loss": 3.6077,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647918286803336e-05,
"loss": 3.6092,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.647079692052284e-05,
"loss": 3.6125,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646241097301232e-05,
"loss": 3.622,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6454041404305535e-05,
"loss": 3.6156,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.644565545679501e-05,
"loss": 3.6018,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643726950928449e-05,
"loss": 3.6184,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642888356177397e-05,
"loss": 3.6033,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.642051399306718e-05,
"loss": 3.6244,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641212804555666e-05,
"loss": 3.6158,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640374209804614e-05,
"loss": 3.6291,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639535615053562e-05,
"loss": 3.6008,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638698658182883e-05,
"loss": 3.6241,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637860063431831e-05,
"loss": 3.6167,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.637021468680779e-05,
"loss": 3.62,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636182873929727e-05,
"loss": 3.617,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635344279178675e-05,
"loss": 3.6035,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634507322307996e-05,
"loss": 3.6259,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633668727556944e-05,
"loss": 3.6269,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632830132805892e-05,
"loss": 3.6191,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.63199153805484e-05,
"loss": 3.6151,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631154581184161e-05,
"loss": 3.621,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630315986433109e-05,
"loss": 3.6144,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629477391682057e-05,
"loss": 3.6077,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628638796931005e-05,
"loss": 3.6222,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627801840060327e-05,
"loss": 3.6183,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.6269632453092747e-05,
"loss": 3.6221,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.6261246505582227e-05,
"loss": 3.6123,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.8455023765563965,
"eval_runtime": 324.7128,
"eval_samples_per_second": 1175.164,
"eval_steps_per_second": 36.725,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.6252860558071707e-05,
"loss": 3.6068,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.6244490989364916e-05,
"loss": 3.597,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.6236105041854396e-05,
"loss": 3.6119,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.6227719094343876e-05,
"loss": 3.6184,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.6219333146833355e-05,
"loss": 3.6224,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.6210963578126565e-05,
"loss": 3.6109,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.6202577630616045e-05,
"loss": 3.6112,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.6194191683105524e-05,
"loss": 3.6054,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.6185805735595004e-05,
"loss": 3.6068,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.617743616688822e-05,
"loss": 3.6062,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.61690502193777e-05,
"loss": 3.6139,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.616066427186718e-05,
"loss": 3.6179,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.615229470316039e-05,
"loss": 3.6198,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.614390875564987e-05,
"loss": 3.6001,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.613552280813935e-05,
"loss": 3.6101,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.612713686062883e-05,
"loss": 3.5864,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.611875091311831e-05,
"loss": 3.6061,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.611036496560779e-05,
"loss": 3.6088,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.610197901809727e-05,
"loss": 3.5994,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.609359307058675e-05,
"loss": 3.6103,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.608522350187996e-05,
"loss": 3.618,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.6076837554369445e-05,
"loss": 3.6128,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.6068451606858925e-05,
"loss": 3.6188,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.6060065659348405e-05,
"loss": 3.6107,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.6051696090641614e-05,
"loss": 3.6101,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.6043310143131094e-05,
"loss": 3.609,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.6034924195620574e-05,
"loss": 3.607,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.6026538248110054e-05,
"loss": 3.613,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.601816867940326e-05,
"loss": 3.6033,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.600978273189274e-05,
"loss": 3.5951,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.600139678438222e-05,
"loss": 3.603,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.59930108368717e-05,
"loss": 3.6154,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598464126816491e-05,
"loss": 3.6138,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.597625532065439e-05,
"loss": 3.6093,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596786937314388e-05,
"loss": 3.6036,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595948342563336e-05,
"loss": 3.6067,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595111385692657e-05,
"loss": 3.6145,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.594272790941605e-05,
"loss": 3.6003,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.593434196190553e-05,
"loss": 3.6023,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.592595601439501e-05,
"loss": 3.5991,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.5917586445688216e-05,
"loss": 3.5978,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.5909200498177696e-05,
"loss": 3.6101,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.5900814550667176e-05,
"loss": 3.6027,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.5892428603156656e-05,
"loss": 3.6083,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.5884059034449865e-05,
"loss": 3.6076,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.5875673086939345e-05,
"loss": 3.61,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.586728713942883e-05,
"loss": 3.6068,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.585890119191831e-05,
"loss": 3.6109,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.585053162321152e-05,
"loss": 3.5783,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.5842145675701e-05,
"loss": 3.6163,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.583375972819048e-05,
"loss": 3.5996,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.582537378067996e-05,
"loss": 3.6125,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581700421197317e-05,
"loss": 3.5992,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.580861826446265e-05,
"loss": 3.598,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.580023231695213e-05,
"loss": 3.5854,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579184636944161e-05,
"loss": 3.6002,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.578347680073482e-05,
"loss": 3.6061,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.57750908532243e-05,
"loss": 3.5905,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.5766704905713786e-05,
"loss": 3.6161,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.575831895820326e-05,
"loss": 3.6021,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.574993301069274e-05,
"loss": 3.5833,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.5741563441985955e-05,
"loss": 3.6084,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.5733177494475435e-05,
"loss": 3.5935,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.572479154696491e-05,
"loss": 3.59,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.571640559945439e-05,
"loss": 3.6032,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.5708036030747604e-05,
"loss": 3.6019,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.5699650083237084e-05,
"loss": 3.5899,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.569126413572656e-05,
"loss": 3.5887,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.568287818821604e-05,
"loss": 3.589,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567450861950925e-05,
"loss": 3.5973,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566612267199873e-05,
"loss": 3.6054,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565773672448821e-05,
"loss": 3.5974,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564935077697769e-05,
"loss": 3.6096,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.564098120827091e-05,
"loss": 3.6021,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.563259526076038e-05,
"loss": 3.6116,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.562420931324986e-05,
"loss": 3.5955,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.561582336573934e-05,
"loss": 3.6092,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.560745379703255e-05,
"loss": 3.5911,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.559906784952203e-05,
"loss": 3.5879,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.559068190201151e-05,
"loss": 3.6,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.558229595450099e-05,
"loss": 3.6069,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.5573926385794206e-05,
"loss": 3.6083,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.5565540438283686e-05,
"loss": 3.608,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.5557154490773166e-05,
"loss": 3.5778,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.5548768543262646e-05,
"loss": 3.5906,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.5540398974555855e-05,
"loss": 3.5995,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.5532013027045335e-05,
"loss": 3.6015,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.5523627079534815e-05,
"loss": 3.5922,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.5515241132024295e-05,
"loss": 3.604,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.5506871563317504e-05,
"loss": 3.6025,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.5498485615806984e-05,
"loss": 3.5984,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.5490099668296464e-05,
"loss": 3.5896,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.5481713720785944e-05,
"loss": 3.5891,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.547334415207916e-05,
"loss": 3.606,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.546495820456864e-05,
"loss": 3.603,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.545657225705812e-05,
"loss": 3.6022,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.54481863095476e-05,
"loss": 3.595,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.543980036203708e-05,
"loss": 3.5942,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.543143079333029e-05,
"loss": 3.6035,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.542304484581977e-05,
"loss": 3.6031,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.541465889830925e-05,
"loss": 3.5963,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.540627295079873e-05,
"loss": 3.5984,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.539790338209194e-05,
"loss": 3.5939,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.538951743458142e-05,
"loss": 3.5951,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.53811314870709e-05,
"loss": 3.5916,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.5372745539560385e-05,
"loss": 3.5895,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.5364375970853594e-05,
"loss": 3.5897,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.5355990023343074e-05,
"loss": 3.6003,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.5347604075832554e-05,
"loss": 3.5941,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.533923450712576e-05,
"loss": 3.5911,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.533084855961524e-05,
"loss": 3.5902,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.532246261210472e-05,
"loss": 3.5981,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.53140766645942e-05,
"loss": 3.6023,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530569071708368e-05,
"loss": 3.591,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529732114837689e-05,
"loss": 3.596,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.528893520086637e-05,
"loss": 3.6042,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.528054925335585e-05,
"loss": 3.6025,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527216330584534e-05,
"loss": 3.5908,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.526379373713855e-05,
"loss": 3.5962,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.525540778962803e-05,
"loss": 3.5932,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524702184211751e-05,
"loss": 3.6038,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523863589460699e-05,
"loss": 3.5883,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.5230266325900196e-05,
"loss": 3.5898,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.5221880378389676e-05,
"loss": 3.5917,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.5213494430879156e-05,
"loss": 3.5984,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.5205108483368636e-05,
"loss": 3.6005,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.5196738914661845e-05,
"loss": 3.584,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.5188352967151325e-05,
"loss": 3.5951,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.5179967019640805e-05,
"loss": 3.582,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.5171581072130285e-05,
"loss": 3.6033,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.51632115034235e-05,
"loss": 3.6001,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.515482555591298e-05,
"loss": 3.6064,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.514643960840246e-05,
"loss": 3.5836,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.513805366089194e-05,
"loss": 3.5986,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.512968409218515e-05,
"loss": 3.5997,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.512129814467463e-05,
"loss": 3.5987,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.511291219716411e-05,
"loss": 3.597,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.510452624965359e-05,
"loss": 3.5852,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.509614030214307e-05,
"loss": 3.6079,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.508777073343628e-05,
"loss": 3.6078,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.507938478592576e-05,
"loss": 3.6014,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.507099883841524e-05,
"loss": 3.5966,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.5062612890904726e-05,
"loss": 3.6011,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.5054243322197935e-05,
"loss": 3.5944,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.5045857374687415e-05,
"loss": 3.5893,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.5037471427176895e-05,
"loss": 3.6031,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.5029085479666374e-05,
"loss": 3.5978,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.5020715910959584e-05,
"loss": 3.6027,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.5012329963449064e-05,
"loss": 3.5925,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 3.8443572521209717,
"eval_runtime": 303.9922,
"eval_samples_per_second": 1255.266,
"eval_steps_per_second": 39.228,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.5003944015938544e-05,
"loss": 3.5957,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.4995558068428023e-05,
"loss": 3.574,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.4987172120917503e-05,
"loss": 3.5938,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.497878617340698e-05,
"loss": 3.6001,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.497041660470019e-05,
"loss": 3.5991,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.496203065718968e-05,
"loss": 3.5926,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.495364470967916e-05,
"loss": 3.5976,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.494525876216863e-05,
"loss": 3.584,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.493688919346185e-05,
"loss": 3.5854,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.492850324595133e-05,
"loss": 3.5859,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.492011729844081e-05,
"loss": 3.5982,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.491173135093028e-05,
"loss": 3.5973,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.49033617822235e-05,
"loss": 3.6018,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.489497583471298e-05,
"loss": 3.5812,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.488658988720246e-05,
"loss": 3.5893,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.487820393969193e-05,
"loss": 3.5665,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.486981799218142e-05,
"loss": 3.5879,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.48614320446709e-05,
"loss": 3.588,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.485304609716038e-05,
"loss": 3.5785,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.484466014964986e-05,
"loss": 3.5916,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.483627420213934e-05,
"loss": 3.5972,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.4827904633432546e-05,
"loss": 3.5947,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.4819518685922026e-05,
"loss": 3.6018,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.4811132738411506e-05,
"loss": 3.5896,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.4802746790900986e-05,
"loss": 3.5933,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.4794377222194195e-05,
"loss": 3.5908,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.4785991274683675e-05,
"loss": 3.5861,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.4777605327173155e-05,
"loss": 3.5953,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.4769219379662635e-05,
"loss": 3.5857,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.476084981095585e-05,
"loss": 3.5736,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.475246386344533e-05,
"loss": 3.5867,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.474407791593481e-05,
"loss": 3.5947,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.473569196842429e-05,
"loss": 3.5936,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.47273223997175e-05,
"loss": 3.5919,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.471893645220698e-05,
"loss": 3.5853,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.471055050469646e-05,
"loss": 3.5884,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.470216455718594e-05,
"loss": 3.5959,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.469379498847915e-05,
"loss": 3.5808,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.468540904096863e-05,
"loss": 3.5838,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.467702309345811e-05,
"loss": 3.5791,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466863714594759e-05,
"loss": 3.5806,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.4660267577240804e-05,
"loss": 3.5877,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.4651881629730284e-05,
"loss": 3.5892,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.4643495682219764e-05,
"loss": 3.5891,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.4635109734709244e-05,
"loss": 3.5868,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.4626723787198724e-05,
"loss": 3.5888,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.461835421849193e-05,
"loss": 3.5874,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.460996827098141e-05,
"loss": 3.5952,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.460158232347089e-05,
"loss": 3.5612,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.459319637596037e-05,
"loss": 3.5963,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.458482680725358e-05,
"loss": 3.5817,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.457644085974306e-05,
"loss": 3.5894,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.456805491223254e-05,
"loss": 3.5822,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.455966896472202e-05,
"loss": 3.5796,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.455129939601524e-05,
"loss": 3.5687,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.454291344850472e-05,
"loss": 3.5787,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.45345275009942e-05,
"loss": 3.5899,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.452614155348368e-05,
"loss": 3.5716,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.451777198477689e-05,
"loss": 3.5989,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.450938603726637e-05,
"loss": 3.5829,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.450100008975585e-05,
"loss": 3.5634,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.449261414224533e-05,
"loss": 3.5903,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.4484244573538536e-05,
"loss": 3.5737,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.4475858626028016e-05,
"loss": 3.5708,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.4467472678517496e-05,
"loss": 3.5807,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.4459086731006976e-05,
"loss": 3.5834,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.445071716230019e-05,
"loss": 3.5727,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.444233121478967e-05,
"loss": 3.5753,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.443394526727915e-05,
"loss": 3.5684,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.442555931976863e-05,
"loss": 3.5756,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.441718975106184e-05,
"loss": 3.5863,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.440880380355132e-05,
"loss": 3.5811,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.44004178560408e-05,
"loss": 3.5903,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.439203190853028e-05,
"loss": 3.5823,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.438366233982349e-05,
"loss": 3.5934,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.437527639231297e-05,
"loss": 3.5785,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.436689044480245e-05,
"loss": 3.5902,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.435850449729193e-05,
"loss": 3.5722,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.4350134928585145e-05,
"loss": 3.5685,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.4341748981074625e-05,
"loss": 3.5822,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.4333363033564105e-05,
"loss": 3.5849,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.4324977086053585e-05,
"loss": 3.5915,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.4316607517346794e-05,
"loss": 3.588,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.4308221569836274e-05,
"loss": 3.5646,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.4299835622325754e-05,
"loss": 3.5703,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.4291449674815234e-05,
"loss": 3.5777,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.428308010610844e-05,
"loss": 3.5844,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.427469415859792e-05,
"loss": 3.5739,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.42663082110874e-05,
"loss": 3.5849,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.425792226357688e-05,
"loss": 3.5889,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.42495526948701e-05,
"loss": 3.5754,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.424116674735958e-05,
"loss": 3.5729,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.423278079984906e-05,
"loss": 3.5744,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.422439485233854e-05,
"loss": 3.5846,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.421602528363175e-05,
"loss": 3.585,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.420763933612123e-05,
"loss": 3.5865,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.419925338861071e-05,
"loss": 3.5782,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.419086744110018e-05,
"loss": 3.5705,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.41824978723934e-05,
"loss": 3.589,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.417411192488288e-05,
"loss": 3.5831,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.416572597737236e-05,
"loss": 3.5821,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.415734002986184e-05,
"loss": 3.5757,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.414897046115505e-05,
"loss": 3.5774,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.414058451364453e-05,
"loss": 3.5747,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.413219856613401e-05,
"loss": 3.5751,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.4123812618623486e-05,
"loss": 3.5741,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.41154430499167e-05,
"loss": 3.5725,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.410705710240618e-05,
"loss": 3.5804,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.4098671154895655e-05,
"loss": 3.5811,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.4090285207385135e-05,
"loss": 3.5696,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.408191563867835e-05,
"loss": 3.5748,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.407352969116783e-05,
"loss": 3.5788,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.406514374365731e-05,
"loss": 3.585,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.405675779614679e-05,
"loss": 3.5696,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.4048388227440006e-05,
"loss": 3.5826,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.4040002279929486e-05,
"loss": 3.5798,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.403161633241896e-05,
"loss": 3.5882,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402323038490844e-05,
"loss": 3.5741,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.4014860816201655e-05,
"loss": 3.5766,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.400647486869113e-05,
"loss": 3.5796,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.399808892118061e-05,
"loss": 3.5827,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.398970297367009e-05,
"loss": 3.5679,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.3981333404963304e-05,
"loss": 3.5747,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.397294745745278e-05,
"loss": 3.5754,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.3964561509942264e-05,
"loss": 3.5793,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.3956175562431744e-05,
"loss": 3.577,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.394780599372496e-05,
"loss": 3.5724,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.393942004621443e-05,
"loss": 3.575,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.393103409870391e-05,
"loss": 3.569,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.392264815119339e-05,
"loss": 3.5876,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.39142785824866e-05,
"loss": 3.5776,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.390589263497608e-05,
"loss": 3.5888,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.389750668746556e-05,
"loss": 3.5657,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.388912073995504e-05,
"loss": 3.5829,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.388075117124825e-05,
"loss": 3.5825,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.387236522373773e-05,
"loss": 3.5803,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.386397927622722e-05,
"loss": 3.5762,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.38555933287167e-05,
"loss": 3.566,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.384722376000991e-05,
"loss": 3.5935,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.383883781249939e-05,
"loss": 3.5904,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.383045186498887e-05,
"loss": 3.5837,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382206591747835e-05,
"loss": 3.5762,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.3813696348771556e-05,
"loss": 3.585,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.3805310401261036e-05,
"loss": 3.5788,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.3796924453750516e-05,
"loss": 3.5672,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.3788538506239996e-05,
"loss": 3.5913,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.3780168937533205e-05,
"loss": 3.5758,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.3771782990022685e-05,
"loss": 3.5862,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.376339704251217e-05,
"loss": 3.5758,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 3.8435018062591553,
"eval_runtime": 304.8505,
"eval_samples_per_second": 1251.732,
"eval_steps_per_second": 39.118,
"step": 992160
},
{
"epoch": 1.0,
"learning_rate": 3.375501109500165e-05,
"loss": 3.5759,
"step": 992256
},
{
"epoch": 1.0,
"learning_rate": 3.374664152629486e-05,
"loss": 3.555,
"step": 992768
},
{
"epoch": 1.0,
"learning_rate": 3.373825557878434e-05,
"loss": 3.5723,
"step": 993280
},
{
"epoch": 1.0,
"learning_rate": 3.372986963127382e-05,
"loss": 3.5888,
"step": 993792
},
{
"epoch": 1.0,
"learning_rate": 3.37214836837633e-05,
"loss": 3.579,
"step": 994304
},
{
"epoch": 1.0,
"learning_rate": 3.371311411505651e-05,
"loss": 3.5766,
"step": 994816
},
{
"epoch": 1.0,
"learning_rate": 3.370472816754599e-05,
"loss": 3.5767,
"step": 995328
},
{
"epoch": 1.0,
"learning_rate": 3.369634222003547e-05,
"loss": 3.5695,
"step": 995840
},
{
"epoch": 1.0,
"learning_rate": 3.368795627252495e-05,
"loss": 3.5636,
"step": 996352
},
{
"epoch": 1.0,
"learning_rate": 3.367958670381816e-05,
"loss": 3.5713,
"step": 996864
},
{
"epoch": 1.0,
"learning_rate": 3.367120075630764e-05,
"loss": 3.5801,
"step": 997376
},
{
"epoch": 1.0,
"learning_rate": 3.3662814808797125e-05,
"loss": 3.5744,
"step": 997888
},
{
"epoch": 1.0,
"learning_rate": 3.3654445240090334e-05,
"loss": 3.5902,
"step": 998400
},
{
"epoch": 1.0,
"learning_rate": 3.3646059292579814e-05,
"loss": 3.562,
"step": 998912
},
{
"epoch": 1.0,
"learning_rate": 3.3637673345069294e-05,
"loss": 3.568,
"step": 999424
},
{
"epoch": 1.0,
"learning_rate": 3.3629287397558774e-05,
"loss": 3.5534,
"step": 999936
},
{
"epoch": 1.0,
"learning_rate": 3.3620901450048254e-05,
"loss": 3.5666,
"step": 1000448
},
{
"epoch": 1.0,
"learning_rate": 3.3612515502537734e-05,
"loss": 3.5728,
"step": 1000960
},
{
"epoch": 1.0,
"learning_rate": 3.3604129555027214e-05,
"loss": 3.5648,
"step": 1001472
},
{
"epoch": 1.0,
"learning_rate": 3.3595743607516694e-05,
"loss": 3.5656,
"step": 1001984
},
{
"epoch": 1.0,
"learning_rate": 3.35873740388099e-05,
"loss": 3.5853,
"step": 1002496
},
{
"epoch": 1.0,
"learning_rate": 3.357898809129938e-05,
"loss": 3.5754,
"step": 1003008
},
{
"epoch": 1.0,
"learning_rate": 3.357060214378886e-05,
"loss": 3.5809,
"step": 1003520
},
{
"epoch": 1.0,
"learning_rate": 3.356221619627834e-05,
"loss": 3.5761,
"step": 1004032
},
{
"epoch": 1.0,
"learning_rate": 3.355384662757156e-05,
"loss": 3.5763,
"step": 1004544
},
{
"epoch": 1.0,
"learning_rate": 3.354546068006104e-05,
"loss": 3.5685,
"step": 1005056
},
{
"epoch": 1.0,
"learning_rate": 3.353707473255052e-05,
"loss": 3.5686,
"step": 1005568
},
{
"epoch": 1.0,
"learning_rate": 3.352868878504e-05,
"loss": 3.579,
"step": 1006080
},
{
"epoch": 1.0,
"learning_rate": 3.352031921633321e-05,
"loss": 3.5684,
"step": 1006592
},
{
"epoch": 1.0,
"learning_rate": 3.351193326882269e-05,
"loss": 3.5528,
"step": 1007104
},
{
"epoch": 1.01,
"learning_rate": 3.350354732131217e-05,
"loss": 3.5726,
"step": 1007616
},
{
"epoch": 1.01,
"learning_rate": 3.349516137380165e-05,
"loss": 3.5743,
"step": 1008128
},
{
"epoch": 1.01,
"learning_rate": 3.348679180509486e-05,
"loss": 3.5772,
"step": 1008640
},
{
"epoch": 1.01,
"learning_rate": 3.3478405857584337e-05,
"loss": 3.5719,
"step": 1009152
},
{
"epoch": 1.01,
"learning_rate": 3.3470019910073817e-05,
"loss": 3.5715,
"step": 1009664
},
{
"epoch": 1.01,
"learning_rate": 3.3461633962563296e-05,
"loss": 3.5721,
"step": 1010176
},
{
"epoch": 1.01,
"learning_rate": 3.345326439385651e-05,
"loss": 3.5791,
"step": 1010688
},
{
"epoch": 1.01,
"learning_rate": 3.344487844634599e-05,
"loss": 3.5583,
"step": 1011200
},
{
"epoch": 1.01,
"learning_rate": 3.343649249883547e-05,
"loss": 3.568,
"step": 1011712
},
{
"epoch": 1.01,
"learning_rate": 3.342810655132495e-05,
"loss": 3.5633,
"step": 1012224
},
{
"epoch": 1.01,
"learning_rate": 3.341973698261816e-05,
"loss": 3.5617,
"step": 1012736
},
{
"epoch": 1.01,
"learning_rate": 3.341135103510764e-05,
"loss": 3.5743,
"step": 1013248
},
{
"epoch": 1.01,
"learning_rate": 3.340296508759712e-05,
"loss": 3.5735,
"step": 1013760
},
{
"epoch": 1.01,
"learning_rate": 3.33945791400866e-05,
"loss": 3.5712,
"step": 1014272
},
{
"epoch": 1.01,
"learning_rate": 3.338620957137981e-05,
"loss": 3.5685,
"step": 1014784
},
{
"epoch": 1.01,
"learning_rate": 3.337782362386929e-05,
"loss": 3.5689,
"step": 1015296
},
{
"epoch": 1.01,
"learning_rate": 3.336943767635877e-05,
"loss": 3.5724,
"step": 1015808
},
{
"epoch": 1.01,
"learning_rate": 3.336105172884825e-05,
"loss": 3.5764,
"step": 1016320
},
{
"epoch": 1.01,
"learning_rate": 3.3352682160141466e-05,
"loss": 3.5466,
"step": 1016832
},
{
"epoch": 1.01,
"learning_rate": 3.3344296212630946e-05,
"loss": 3.5777,
"step": 1017344
},
{
"epoch": 1.01,
"learning_rate": 3.3335910265120426e-05,
"loss": 3.5679,
"step": 1017856
},
{
"epoch": 1.01,
"learning_rate": 3.3327524317609906e-05,
"loss": 3.5729,
"step": 1018368
},
{
"epoch": 1.01,
"learning_rate": 3.3319154748903115e-05,
"loss": 3.5659,
"step": 1018880
},
{
"epoch": 1.01,
"learning_rate": 3.3310768801392595e-05,
"loss": 3.5603,
"step": 1019392
},
{
"epoch": 1.01,
"learning_rate": 3.3302382853882075e-05,
"loss": 3.5547,
"step": 1019904
},
{
"epoch": 1.01,
"learning_rate": 3.3293996906371555e-05,
"loss": 3.5593,
"step": 1020416
},
{
"epoch": 1.01,
"learning_rate": 3.3285627337664764e-05,
"loss": 3.5742,
"step": 1020928
},
{
"epoch": 1.01,
"learning_rate": 3.3277241390154244e-05,
"loss": 3.5528,
"step": 1021440
},
{
"epoch": 1.01,
"learning_rate": 3.3268855442643724e-05,
"loss": 3.583,
"step": 1021952
},
{
"epoch": 1.01,
"learning_rate": 3.3260469495133204e-05,
"loss": 3.5662,
"step": 1022464
},
{
"epoch": 1.01,
"learning_rate": 3.325209992642642e-05,
"loss": 3.5488,
"step": 1022976
},
{
"epoch": 1.01,
"learning_rate": 3.32437139789159e-05,
"loss": 3.5738,
"step": 1023488
},
{
"epoch": 1.01,
"learning_rate": 3.323532803140538e-05,
"loss": 3.553,
"step": 1024000
},
{
"epoch": 1.01,
"learning_rate": 3.322694208389486e-05,
"loss": 3.5611,
"step": 1024512
},
{
"epoch": 1.01,
"learning_rate": 3.321857251518807e-05,
"loss": 3.5597,
"step": 1025024
},
{
"epoch": 1.01,
"learning_rate": 3.321018656767755e-05,
"loss": 3.5713,
"step": 1025536
},
{
"epoch": 1.01,
"learning_rate": 3.320180062016703e-05,
"loss": 3.5502,
"step": 1026048
},
{
"epoch": 1.01,
"learning_rate": 3.319341467265651e-05,
"loss": 3.5611,
"step": 1026560
},
{
"epoch": 1.01,
"learning_rate": 3.318504510394972e-05,
"loss": 3.55,
"step": 1027072
},
{
"epoch": 1.01,
"learning_rate": 3.31766591564392e-05,
"loss": 3.5593,
"step": 1027584
},
{
"epoch": 1.01,
"learning_rate": 3.316827320892868e-05,
"loss": 3.5717,
"step": 1028096
},
{
"epoch": 1.01,
"learning_rate": 3.315988726141816e-05,
"loss": 3.5605,
"step": 1028608
},
{
"epoch": 1.01,
"learning_rate": 3.315151769271137e-05,
"loss": 3.5728,
"step": 1029120
},
{
"epoch": 1.01,
"learning_rate": 3.314313174520085e-05,
"loss": 3.5631,
"step": 1029632
},
{
"epoch": 1.01,
"learning_rate": 3.313474579769033e-05,
"loss": 3.5807,
"step": 1030144
},
{
"epoch": 1.01,
"learning_rate": 3.3126359850179806e-05,
"loss": 3.5599,
"step": 1030656
},
{
"epoch": 1.01,
"learning_rate": 3.311799028147302e-05,
"loss": 3.5714,
"step": 1031168
},
{
"epoch": 1.01,
"learning_rate": 3.31096043339625e-05,
"loss": 3.5579,
"step": 1031680
},
{
"epoch": 1.01,
"learning_rate": 3.310121838645198e-05,
"loss": 3.5513,
"step": 1032192
},
{
"epoch": 1.01,
"learning_rate": 3.3092832438941455e-05,
"loss": 3.5666,
"step": 1032704
},
{
"epoch": 1.01,
"learning_rate": 3.308446287023467e-05,
"loss": 3.5646,
"step": 1033216
},
{
"epoch": 1.01,
"learning_rate": 3.307607692272415e-05,
"loss": 3.5725,
"step": 1033728
},
{
"epoch": 1.01,
"learning_rate": 3.3067690975213624e-05,
"loss": 3.5751,
"step": 1034240
},
{
"epoch": 1.01,
"learning_rate": 3.305930502770311e-05,
"loss": 3.5536,
"step": 1034752
},
{
"epoch": 1.01,
"learning_rate": 3.305093545899633e-05,
"loss": 3.5513,
"step": 1035264
},
{
"epoch": 1.01,
"learning_rate": 3.304254951148581e-05,
"loss": 3.56,
"step": 1035776
},
{
"epoch": 1.01,
"learning_rate": 3.303416356397528e-05,
"loss": 3.5658,
"step": 1036288
},
{
"epoch": 1.01,
"learning_rate": 3.302577761646476e-05,
"loss": 3.5611,
"step": 1036800
},
{
"epoch": 1.01,
"learning_rate": 3.3017408047757976e-05,
"loss": 3.5635,
"step": 1037312
},
{
"epoch": 1.01,
"learning_rate": 3.300902210024745e-05,
"loss": 3.5706,
"step": 1037824
},
{
"epoch": 1.02,
"learning_rate": 3.300063615273693e-05,
"loss": 3.5631,
"step": 1038336
},
{
"epoch": 1.02,
"learning_rate": 3.299225020522641e-05,
"loss": 3.5584,
"step": 1038848
},
{
"epoch": 1.02,
"learning_rate": 3.2983880636519625e-05,
"loss": 3.5517,
"step": 1039360
},
{
"epoch": 1.02,
"learning_rate": 3.29754946890091e-05,
"loss": 3.5733,
"step": 1039872
},
{
"epoch": 1.02,
"learning_rate": 3.296710874149858e-05,
"loss": 3.5678,
"step": 1040384
},
{
"epoch": 1.02,
"learning_rate": 3.2958722793988065e-05,
"loss": 3.5697,
"step": 1040896
},
{
"epoch": 1.02,
"learning_rate": 3.295035322528128e-05,
"loss": 3.5578,
"step": 1041408
},
{
"epoch": 1.02,
"learning_rate": 3.2941967277770754e-05,
"loss": 3.5574,
"step": 1041920
},
{
"epoch": 1.02,
"learning_rate": 3.2933581330260234e-05,
"loss": 3.572,
"step": 1042432
},
{
"epoch": 1.02,
"learning_rate": 3.2925195382749714e-05,
"loss": 3.5657,
"step": 1042944
},
{
"epoch": 1.02,
"learning_rate": 3.291682581404292e-05,
"loss": 3.5628,
"step": 1043456
},
{
"epoch": 1.02,
"learning_rate": 3.29084398665324e-05,
"loss": 3.5606,
"step": 1043968
},
{
"epoch": 1.02,
"learning_rate": 3.290005391902188e-05,
"loss": 3.5568,
"step": 1044480
},
{
"epoch": 1.02,
"learning_rate": 3.289166797151136e-05,
"loss": 3.5621,
"step": 1044992
},
{
"epoch": 1.02,
"learning_rate": 3.288329840280457e-05,
"loss": 3.5595,
"step": 1045504
},
{
"epoch": 1.02,
"learning_rate": 3.287491245529405e-05,
"loss": 3.5526,
"step": 1046016
},
{
"epoch": 1.02,
"learning_rate": 3.286652650778353e-05,
"loss": 3.5581,
"step": 1046528
},
{
"epoch": 1.02,
"learning_rate": 3.285814056027302e-05,
"loss": 3.5622,
"step": 1047040
},
{
"epoch": 1.02,
"learning_rate": 3.284977099156623e-05,
"loss": 3.5675,
"step": 1047552
},
{
"epoch": 1.02,
"learning_rate": 3.284138504405571e-05,
"loss": 3.5503,
"step": 1048064
},
{
"epoch": 1.02,
"learning_rate": 3.283299909654519e-05,
"loss": 3.5603,
"step": 1048576
},
{
"epoch": 1.02,
"learning_rate": 3.282461314903467e-05,
"loss": 3.5581,
"step": 1049088
},
{
"epoch": 1.02,
"learning_rate": 3.2816243580327877e-05,
"loss": 3.571,
"step": 1049600
},
{
"epoch": 1.02,
"learning_rate": 3.2807857632817357e-05,
"loss": 3.5565,
"step": 1050112
},
{
"epoch": 1.02,
"learning_rate": 3.2799471685306836e-05,
"loss": 3.5594,
"step": 1050624
},
{
"epoch": 1.02,
"learning_rate": 3.2791085737796316e-05,
"loss": 3.5673,
"step": 1051136
},
{
"epoch": 1.02,
"learning_rate": 3.2782716169089526e-05,
"loss": 3.5727,
"step": 1051648
},
{
"epoch": 1.02,
"learning_rate": 3.2774330221579005e-05,
"loss": 3.5547,
"step": 1052160
},
{
"epoch": 1.02,
"learning_rate": 3.2765944274068485e-05,
"loss": 3.5591,
"step": 1052672
},
{
"epoch": 1.02,
"learning_rate": 3.275755832655797e-05,
"loss": 3.5631,
"step": 1053184
},
{
"epoch": 1.02,
"learning_rate": 3.274918875785118e-05,
"loss": 3.5631,
"step": 1053696
},
{
"epoch": 1.02,
"learning_rate": 3.274080281034066e-05,
"loss": 3.5531,
"step": 1054208
},
{
"epoch": 1.02,
"learning_rate": 3.273241686283014e-05,
"loss": 3.5592,
"step": 1054720
},
{
"epoch": 1.02,
"learning_rate": 3.272403091531962e-05,
"loss": 3.5559,
"step": 1055232
},
{
"epoch": 1.02,
"learning_rate": 3.271566134661283e-05,
"loss": 3.5633,
"step": 1055744
},
{
"epoch": 1.02,
"learning_rate": 3.270727539910231e-05,
"loss": 3.5617,
"step": 1056256
},
{
"epoch": 1.02,
"learning_rate": 3.269888945159179e-05,
"loss": 3.5536,
"step": 1056768
},
{
"epoch": 1.02,
"learning_rate": 3.269050350408127e-05,
"loss": 3.5606,
"step": 1057280
},
{
"epoch": 1.02,
"learning_rate": 3.268213393537448e-05,
"loss": 3.5522,
"step": 1057792
},
{
"epoch": 1.02,
"learning_rate": 3.267374798786396e-05,
"loss": 3.567,
"step": 1058304
},
{
"epoch": 1.02,
"learning_rate": 3.266536204035344e-05,
"loss": 3.5615,
"step": 1058816
},
{
"epoch": 1.02,
"learning_rate": 3.2656976092842926e-05,
"loss": 3.572,
"step": 1059328
},
{
"epoch": 1.02,
"learning_rate": 3.2648606524136135e-05,
"loss": 3.5503,
"step": 1059840
},
{
"epoch": 1.02,
"learning_rate": 3.2640220576625615e-05,
"loss": 3.5652,
"step": 1060352
},
{
"epoch": 1.02,
"learning_rate": 3.2631834629115095e-05,
"loss": 3.5668,
"step": 1060864
},
{
"epoch": 1.02,
"learning_rate": 3.2623448681604575e-05,
"loss": 3.5612,
"step": 1061376
},
{
"epoch": 1.02,
"learning_rate": 3.2615079112897784e-05,
"loss": 3.5604,
"step": 1061888
},
{
"epoch": 1.02,
"learning_rate": 3.2606693165387264e-05,
"loss": 3.5508,
"step": 1062400
},
{
"epoch": 1.02,
"learning_rate": 3.2598307217876744e-05,
"loss": 3.5748,
"step": 1062912
},
{
"epoch": 1.02,
"learning_rate": 3.2589921270366224e-05,
"loss": 3.5722,
"step": 1063424
},
{
"epoch": 1.02,
"learning_rate": 3.258155170165943e-05,
"loss": 3.567,
"step": 1063936
},
{
"epoch": 1.02,
"learning_rate": 3.257316575414891e-05,
"loss": 3.56,
"step": 1064448
},
{
"epoch": 1.02,
"learning_rate": 3.256477980663839e-05,
"loss": 3.5702,
"step": 1064960
},
{
"epoch": 1.02,
"learning_rate": 3.255639385912787e-05,
"loss": 3.5607,
"step": 1065472
},
{
"epoch": 1.02,
"learning_rate": 3.254802429042109e-05,
"loss": 3.5514,
"step": 1065984
},
{
"epoch": 1.02,
"learning_rate": 3.253963834291057e-05,
"loss": 3.5744,
"step": 1066496
},
{
"epoch": 1.02,
"learning_rate": 3.253125239540005e-05,
"loss": 3.5591,
"step": 1067008
},
{
"epoch": 1.02,
"learning_rate": 3.252286644788953e-05,
"loss": 3.5732,
"step": 1067520
},
{
"epoch": 1.02,
"learning_rate": 3.251449687918274e-05,
"loss": 3.5527,
"step": 1068032
},
{
"epoch": 1.03,
"eval_loss": 3.8457250595092773,
"eval_runtime": 303.8283,
"eval_samples_per_second": 1255.943,
"eval_steps_per_second": 39.249,
"step": 1068480
},
{
"epoch": 0.0,
"learning_rate": 3.250611093167222e-05,
"loss": 3.5633,
"step": 1068544
},
{
"epoch": 0.0,
"learning_rate": 3.24977249841617e-05,
"loss": 3.5434,
"step": 1069056
},
{
"epoch": 0.0,
"learning_rate": 3.248933903665118e-05,
"loss": 3.5534,
"step": 1069568
},
{
"epoch": 0.0,
"learning_rate": 3.248095308914066e-05,
"loss": 3.571,
"step": 1070080
},
{
"epoch": 0.0,
"learning_rate": 3.247256714163014e-05,
"loss": 3.5634,
"step": 1070592
},
{
"epoch": 0.0,
"learning_rate": 3.2464197572923346e-05,
"loss": 3.5599,
"step": 1071104
},
{
"epoch": 0.0,
"learning_rate": 3.2455811625412826e-05,
"loss": 3.5536,
"step": 1071616
},
{
"epoch": 0.0,
"learning_rate": 3.244742567790231e-05,
"loss": 3.5517,
"step": 1072128
},
{
"epoch": 0.0,
"learning_rate": 3.243903973039179e-05,
"loss": 3.5512,
"step": 1072640
},
{
"epoch": 0.0,
"learning_rate": 3.2430670161685e-05,
"loss": 3.5575,
"step": 1073152
},
{
"epoch": 0.0,
"learning_rate": 3.242228421417448e-05,
"loss": 3.5609,
"step": 1073664
},
{
"epoch": 0.0,
"learning_rate": 3.241389826666396e-05,
"loss": 3.5636,
"step": 1074176
},
{
"epoch": 0.0,
"learning_rate": 3.240552869795717e-05,
"loss": 3.5706,
"step": 1074688
},
{
"epoch": 0.0,
"learning_rate": 3.239714275044665e-05,
"loss": 3.5469,
"step": 1075200
},
{
"epoch": 0.0,
"learning_rate": 3.238875680293613e-05,
"loss": 3.5554,
"step": 1075712
},
{
"epoch": 0.0,
"learning_rate": 3.238037085542561e-05,
"loss": 3.5342,
"step": 1076224
},
{
"epoch": 0.0,
"learning_rate": 3.237198490791509e-05,
"loss": 3.5526,
"step": 1076736
},
{
"epoch": 0.0,
"learning_rate": 3.236359896040457e-05,
"loss": 3.5521,
"step": 1077248
},
{
"epoch": 0.0,
"learning_rate": 3.235521301289405e-05,
"loss": 3.5529,
"step": 1077760
},
{
"epoch": 0.0,
"learning_rate": 3.234682706538353e-05,
"loss": 3.5463,
"step": 1078272
},
{
"epoch": 0.0,
"learning_rate": 3.233844111787301e-05,
"loss": 3.5705,
"step": 1078784
},
{
"epoch": 0.0,
"learning_rate": 3.233007154916623e-05,
"loss": 3.558,
"step": 1079296
},
{
"epoch": 0.0,
"learning_rate": 3.232168560165571e-05,
"loss": 3.5645,
"step": 1079808
},
{
"epoch": 0.0,
"learning_rate": 3.231329965414518e-05,
"loss": 3.5571,
"step": 1080320
},
{
"epoch": 0.0,
"learning_rate": 3.230491370663466e-05,
"loss": 3.566,
"step": 1080832
},
{
"epoch": 0.0,
"learning_rate": 3.2296544137927876e-05,
"loss": 3.5493,
"step": 1081344
},
{
"epoch": 0.0,
"learning_rate": 3.2288158190417356e-05,
"loss": 3.5522,
"step": 1081856
},
{
"epoch": 0.0,
"learning_rate": 3.227977224290683e-05,
"loss": 3.5658,
"step": 1082368
},
{
"epoch": 0.0,
"learning_rate": 3.227138629539631e-05,
"loss": 3.5509,
"step": 1082880
},
{
"epoch": 0.0,
"learning_rate": 3.2263016726689525e-05,
"loss": 3.539,
"step": 1083392
},
{
"epoch": 0.01,
"learning_rate": 3.2254630779179005e-05,
"loss": 3.5533,
"step": 1083904
},
{
"epoch": 0.01,
"learning_rate": 3.2246244831668485e-05,
"loss": 3.555,
"step": 1084416
},
{
"epoch": 0.01,
"learning_rate": 3.2237858884157964e-05,
"loss": 3.5627,
"step": 1084928
},
{
"epoch": 0.01,
"learning_rate": 3.2229472936647444e-05,
"loss": 3.5563,
"step": 1085440
},
{
"epoch": 0.01,
"learning_rate": 3.2221103367940654e-05,
"loss": 3.5529,
"step": 1085952
},
{
"epoch": 0.01,
"learning_rate": 3.2212717420430134e-05,
"loss": 3.5585,
"step": 1086464
},
{
"epoch": 0.01,
"learning_rate": 3.2204331472919613e-05,
"loss": 3.5631,
"step": 1086976
},
{
"epoch": 0.01,
"learning_rate": 3.2195945525409093e-05,
"loss": 3.5417,
"step": 1087488
},
{
"epoch": 0.01,
"learning_rate": 3.21875759567023e-05,
"loss": 3.5555,
"step": 1088000
},
{
"epoch": 0.01,
"learning_rate": 3.217919000919178e-05,
"loss": 3.5463,
"step": 1088512
},
{
"epoch": 0.01,
"learning_rate": 3.217080406168126e-05,
"loss": 3.5433,
"step": 1089024
},
{
"epoch": 0.01,
"learning_rate": 3.216241811417074e-05,
"loss": 3.556,
"step": 1089536
},
{
"epoch": 0.01,
"learning_rate": 3.215404854546396e-05,
"loss": 3.5631,
"step": 1090048
},
{
"epoch": 0.01,
"learning_rate": 3.214566259795344e-05,
"loss": 3.5511,
"step": 1090560
},
{
"epoch": 0.01,
"learning_rate": 3.213727665044292e-05,
"loss": 3.5549,
"step": 1091072
},
{
"epoch": 0.01,
"learning_rate": 3.21288907029324e-05,
"loss": 3.5566,
"step": 1091584
},
{
"epoch": 0.01,
"learning_rate": 3.212052113422561e-05,
"loss": 3.552,
"step": 1092096
},
{
"epoch": 0.01,
"learning_rate": 3.211213518671509e-05,
"loss": 3.5583,
"step": 1092608
},
{
"epoch": 0.01,
"learning_rate": 3.210374923920457e-05,
"loss": 3.5316,
"step": 1093120
},
{
"epoch": 0.01,
"learning_rate": 3.209536329169405e-05,
"loss": 3.559,
"step": 1093632
},
{
"epoch": 0.01,
"learning_rate": 3.2086993722987256e-05,
"loss": 3.5535,
"step": 1094144
},
{
"epoch": 0.01,
"learning_rate": 3.2078607775476736e-05,
"loss": 3.5601,
"step": 1094656
},
{
"epoch": 0.01,
"learning_rate": 3.2070221827966216e-05,
"loss": 3.5485,
"step": 1095168
},
{
"epoch": 0.01,
"learning_rate": 3.2061835880455696e-05,
"loss": 3.5438,
"step": 1095680
},
{
"epoch": 0.01,
"learning_rate": 3.205346631174891e-05,
"loss": 3.5391,
"step": 1096192
},
{
"epoch": 0.01,
"learning_rate": 3.204508036423839e-05,
"loss": 3.5435,
"step": 1096704
},
{
"epoch": 0.01,
"learning_rate": 3.203669441672787e-05,
"loss": 3.5548,
"step": 1097216
},
{
"epoch": 0.01,
"learning_rate": 3.202830846921735e-05,
"loss": 3.5379,
"step": 1097728
},
{
"epoch": 0.01,
"learning_rate": 3.201993890051056e-05,
"loss": 3.5671,
"step": 1098240
},
{
"epoch": 0.01,
"learning_rate": 3.201155295300004e-05,
"loss": 3.5497,
"step": 1098752
},
{
"epoch": 0.01,
"learning_rate": 3.200316700548952e-05,
"loss": 3.5391,
"step": 1099264
},
{
"epoch": 0.01,
"learning_rate": 3.1994781057979e-05,
"loss": 3.5524,
"step": 1099776
},
{
"epoch": 0.01,
"learning_rate": 3.198641148927221e-05,
"loss": 3.5364,
"step": 1100288
},
{
"epoch": 0.01,
"learning_rate": 3.197802554176169e-05,
"loss": 3.5434,
"step": 1100800
},
{
"epoch": 0.01,
"learning_rate": 3.196963959425117e-05,
"loss": 3.5454,
"step": 1101312
},
{
"epoch": 0.01,
"learning_rate": 3.196125364674065e-05,
"loss": 3.5554,
"step": 1101824
},
{
"epoch": 0.01,
"learning_rate": 3.1952884078033866e-05,
"loss": 3.5357,
"step": 1102336
},
{
"epoch": 0.01,
"learning_rate": 3.1944498130523346e-05,
"loss": 3.545,
"step": 1102848
},
{
"epoch": 0.01,
"learning_rate": 3.1936112183012825e-05,
"loss": 3.5333,
"step": 1103360
},
{
"epoch": 0.01,
"learning_rate": 3.1927726235502305e-05,
"loss": 3.5448,
"step": 1103872
},
{
"epoch": 0.01,
"learning_rate": 3.1919356666795515e-05,
"loss": 3.5536,
"step": 1104384
},
{
"epoch": 0.01,
"learning_rate": 3.1910970719284995e-05,
"loss": 3.5498,
"step": 1104896
},
{
"epoch": 0.01,
"learning_rate": 3.1902584771774474e-05,
"loss": 3.5552,
"step": 1105408
},
{
"epoch": 0.01,
"learning_rate": 3.1894198824263954e-05,
"loss": 3.5499,
"step": 1105920
},
{
"epoch": 0.01,
"learning_rate": 3.1885829255557164e-05,
"loss": 3.5632,
"step": 1106432
},
{
"epoch": 0.01,
"learning_rate": 3.1877443308046643e-05,
"loss": 3.5433,
"step": 1106944
},
{
"epoch": 0.01,
"learning_rate": 3.1869057360536123e-05,
"loss": 3.5547,
"step": 1107456
},
{
"epoch": 0.01,
"learning_rate": 3.18606714130256e-05,
"loss": 3.5435,
"step": 1107968
},
{
"epoch": 0.01,
"learning_rate": 3.185230184431882e-05,
"loss": 3.5388,
"step": 1108480
},
{
"epoch": 0.01,
"learning_rate": 3.18439158968083e-05,
"loss": 3.5494,
"step": 1108992
},
{
"epoch": 0.01,
"learning_rate": 3.183552994929778e-05,
"loss": 3.5473,
"step": 1109504
},
{
"epoch": 0.01,
"learning_rate": 3.182714400178726e-05,
"loss": 3.5566,
"step": 1110016
},
{
"epoch": 0.01,
"learning_rate": 3.181877443308047e-05,
"loss": 3.5581,
"step": 1110528
},
{
"epoch": 0.01,
"learning_rate": 3.181038848556995e-05,
"loss": 3.5454,
"step": 1111040
},
{
"epoch": 0.01,
"learning_rate": 3.180200253805943e-05,
"loss": 3.5311,
"step": 1111552
},
{
"epoch": 0.01,
"learning_rate": 3.179361659054891e-05,
"loss": 3.5431,
"step": 1112064
},
{
"epoch": 0.01,
"learning_rate": 3.178524702184212e-05,
"loss": 3.5481,
"step": 1112576
},
{
"epoch": 0.01,
"learning_rate": 3.17768610743316e-05,
"loss": 3.546,
"step": 1113088
},
{
"epoch": 0.01,
"learning_rate": 3.176847512682108e-05,
"loss": 3.5503,
"step": 1113600
},
{
"epoch": 0.01,
"learning_rate": 3.176008917931056e-05,
"loss": 3.5509,
"step": 1114112
},
{
"epoch": 0.02,
"learning_rate": 3.175170323180004e-05,
"loss": 3.5482,
"step": 1114624
},
{
"epoch": 0.02,
"learning_rate": 3.174333366309325e-05,
"loss": 3.5401,
"step": 1115136
},
{
"epoch": 0.02,
"learning_rate": 3.173494771558273e-05,
"loss": 3.5417,
"step": 1115648
},
{
"epoch": 0.02,
"learning_rate": 3.172656176807221e-05,
"loss": 3.5516,
"step": 1116160
},
{
"epoch": 0.02,
"learning_rate": 3.171819219936542e-05,
"loss": 3.555,
"step": 1116672
},
{
"epoch": 0.02,
"learning_rate": 3.17098062518549e-05,
"loss": 3.5505,
"step": 1117184
},
{
"epoch": 0.02,
"learning_rate": 3.170142030434438e-05,
"loss": 3.5421,
"step": 1117696
},
{
"epoch": 0.02,
"learning_rate": 3.169303435683386e-05,
"loss": 3.539,
"step": 1118208
},
{
"epoch": 0.02,
"learning_rate": 3.168466478812707e-05,
"loss": 3.5566,
"step": 1118720
},
{
"epoch": 0.02,
"learning_rate": 3.167627884061655e-05,
"loss": 3.5517,
"step": 1119232
},
{
"epoch": 0.02,
"learning_rate": 3.166789289310603e-05,
"loss": 3.5461,
"step": 1119744
},
{
"epoch": 0.02,
"learning_rate": 3.165950694559551e-05,
"loss": 3.5497,
"step": 1120256
},
{
"epoch": 0.02,
"learning_rate": 3.165113737688872e-05,
"loss": 3.5382,
"step": 1120768
},
{
"epoch": 0.02,
"learning_rate": 3.1642751429378207e-05,
"loss": 3.5461,
"step": 1121280
},
{
"epoch": 0.02,
"learning_rate": 3.1634365481867686e-05,
"loss": 3.5464,
"step": 1121792
},
{
"epoch": 0.02,
"learning_rate": 3.1625979534357166e-05,
"loss": 3.5359,
"step": 1122304
},
{
"epoch": 0.02,
"learning_rate": 3.1617609965650376e-05,
"loss": 3.5425,
"step": 1122816
},
{
"epoch": 0.02,
"learning_rate": 3.1609224018139856e-05,
"loss": 3.5447,
"step": 1123328
},
{
"epoch": 0.02,
"learning_rate": 3.1600838070629335e-05,
"loss": 3.5538,
"step": 1123840
},
{
"epoch": 0.02,
"learning_rate": 3.1592452123118815e-05,
"loss": 3.5339,
"step": 1124352
},
{
"epoch": 0.02,
"learning_rate": 3.1584082554412025e-05,
"loss": 3.5472,
"step": 1124864
},
{
"epoch": 0.02,
"learning_rate": 3.1575696606901504e-05,
"loss": 3.5385,
"step": 1125376
},
{
"epoch": 0.02,
"learning_rate": 3.1567310659390984e-05,
"loss": 3.5563,
"step": 1125888
},
{
"epoch": 0.02,
"learning_rate": 3.1558924711880464e-05,
"loss": 3.5388,
"step": 1126400
},
{
"epoch": 0.02,
"learning_rate": 3.1550555143173673e-05,
"loss": 3.5449,
"step": 1126912
},
{
"epoch": 0.02,
"learning_rate": 3.154216919566316e-05,
"loss": 3.553,
"step": 1127424
},
{
"epoch": 0.02,
"learning_rate": 3.153378324815264e-05,
"loss": 3.5579,
"step": 1127936
},
{
"epoch": 0.02,
"learning_rate": 3.152539730064212e-05,
"loss": 3.5388,
"step": 1128448
},
{
"epoch": 0.02,
"learning_rate": 3.151702773193533e-05,
"loss": 3.5383,
"step": 1128960
},
{
"epoch": 0.02,
"learning_rate": 3.150864178442481e-05,
"loss": 3.5519,
"step": 1129472
},
{
"epoch": 0.02,
"learning_rate": 3.150025583691429e-05,
"loss": 3.5473,
"step": 1129984
},
{
"epoch": 0.02,
"learning_rate": 3.149186988940377e-05,
"loss": 3.5341,
"step": 1130496
},
{
"epoch": 0.02,
"learning_rate": 3.148350032069698e-05,
"loss": 3.5403,
"step": 1131008
},
{
"epoch": 0.02,
"learning_rate": 3.147511437318646e-05,
"loss": 3.5417,
"step": 1131520
},
{
"epoch": 0.02,
"learning_rate": 3.146672842567594e-05,
"loss": 3.5495,
"step": 1132032
},
{
"epoch": 0.02,
"learning_rate": 3.145834247816542e-05,
"loss": 3.5459,
"step": 1132544
},
{
"epoch": 0.02,
"learning_rate": 3.144997290945863e-05,
"loss": 3.5363,
"step": 1133056
},
{
"epoch": 0.02,
"learning_rate": 3.1441586961948114e-05,
"loss": 3.5485,
"step": 1133568
},
{
"epoch": 0.02,
"learning_rate": 3.1433201014437594e-05,
"loss": 3.5386,
"step": 1134080
},
{
"epoch": 0.02,
"learning_rate": 3.1424815066927074e-05,
"loss": 3.5464,
"step": 1134592
},
{
"epoch": 0.02,
"learning_rate": 3.141644549822028e-05,
"loss": 3.5492,
"step": 1135104
},
{
"epoch": 0.02,
"learning_rate": 3.140805955070976e-05,
"loss": 3.5523,
"step": 1135616
},
{
"epoch": 0.02,
"learning_rate": 3.139967360319924e-05,
"loss": 3.5431,
"step": 1136128
},
{
"epoch": 0.02,
"learning_rate": 3.139128765568872e-05,
"loss": 3.5421,
"step": 1136640
},
{
"epoch": 0.02,
"learning_rate": 3.138291808698193e-05,
"loss": 3.5534,
"step": 1137152
},
{
"epoch": 0.02,
"learning_rate": 3.137453213947141e-05,
"loss": 3.5466,
"step": 1137664
},
{
"epoch": 0.02,
"learning_rate": 3.136614619196089e-05,
"loss": 3.547,
"step": 1138176
},
{
"epoch": 0.02,
"learning_rate": 3.135776024445037e-05,
"loss": 3.5368,
"step": 1138688
},
{
"epoch": 0.02,
"learning_rate": 3.134937429693985e-05,
"loss": 3.5635,
"step": 1139200
},
{
"epoch": 0.02,
"learning_rate": 3.134100472823307e-05,
"loss": 3.5511,
"step": 1139712
},
{
"epoch": 0.02,
"learning_rate": 3.133261878072255e-05,
"loss": 3.5544,
"step": 1140224
},
{
"epoch": 0.02,
"learning_rate": 3.132423283321203e-05,
"loss": 3.5441,
"step": 1140736
},
{
"epoch": 0.02,
"learning_rate": 3.13158468857015e-05,
"loss": 3.5538,
"step": 1141248
},
{
"epoch": 0.02,
"learning_rate": 3.1307477316994717e-05,
"loss": 3.5448,
"step": 1141760
},
{
"epoch": 0.02,
"learning_rate": 3.1299091369484196e-05,
"loss": 3.5345,
"step": 1142272
},
{
"epoch": 0.02,
"learning_rate": 3.1290705421973676e-05,
"loss": 3.5597,
"step": 1142784
},
{
"epoch": 0.02,
"learning_rate": 3.1282335853266886e-05,
"loss": 3.5457,
"step": 1143296
},
{
"epoch": 0.02,
"learning_rate": 3.1273949905756365e-05,
"loss": 3.5568,
"step": 1143808
},
{
"epoch": 0.02,
"learning_rate": 3.1265563958245845e-05,
"loss": 3.5374,
"step": 1144320
},
{
"epoch": 0.03,
"eval_loss": 3.8461270332336426,
"eval_runtime": 304.3199,
"eval_samples_per_second": 1253.914,
"eval_steps_per_second": 39.186,
"step": 1144800
},
{
"epoch": 1.0,
"learning_rate": 3.1257178010735325e-05,
"loss": 3.543,
"step": 1144832
},
{
"epoch": 1.0,
"learning_rate": 3.1248808442028534e-05,
"loss": 3.532,
"step": 1145344
},
{
"epoch": 1.0,
"learning_rate": 3.124042249451802e-05,
"loss": 3.537,
"step": 1145856
},
{
"epoch": 1.0,
"learning_rate": 3.12320365470075e-05,
"loss": 3.5532,
"step": 1146368
},
{
"epoch": 1.0,
"learning_rate": 3.1223650599496974e-05,
"loss": 3.5479,
"step": 1146880
},
{
"epoch": 1.0,
"learning_rate": 3.121528103079019e-05,
"loss": 3.5474,
"step": 1147392
},
{
"epoch": 1.0,
"learning_rate": 3.120689508327967e-05,
"loss": 3.5373,
"step": 1147904
},
{
"epoch": 1.0,
"learning_rate": 3.119850913576915e-05,
"loss": 3.5381,
"step": 1148416
},
{
"epoch": 1.0,
"learning_rate": 3.119012318825862e-05,
"loss": 3.536,
"step": 1148928
},
{
"epoch": 1.0,
"learning_rate": 3.118175361955184e-05,
"loss": 3.54,
"step": 1149440
},
{
"epoch": 1.0,
"learning_rate": 3.117336767204132e-05,
"loss": 3.5449,
"step": 1149952
},
{
"epoch": 1.0,
"learning_rate": 3.11649817245308e-05,
"loss": 3.5486,
"step": 1150464
},
{
"epoch": 1.0,
"learning_rate": 3.115659577702027e-05,
"loss": 3.557,
"step": 1150976
},
{
"epoch": 1.0,
"learning_rate": 3.114822620831349e-05,
"loss": 3.5334,
"step": 1151488
},
{
"epoch": 1.0,
"learning_rate": 3.1139840260802975e-05,
"loss": 3.5398,
"step": 1152000
},
{
"epoch": 1.0,
"learning_rate": 3.113145431329245e-05,
"loss": 3.5199,
"step": 1152512
},
{
"epoch": 1.0,
"learning_rate": 3.112306836578193e-05,
"loss": 3.5375,
"step": 1153024
},
{
"epoch": 1.0,
"learning_rate": 3.1114698797075144e-05,
"loss": 3.5339,
"step": 1153536
},
{
"epoch": 1.0,
"learning_rate": 3.1106312849564624e-05,
"loss": 3.5382,
"step": 1154048
},
{
"epoch": 1.0,
"learning_rate": 3.10979269020541e-05,
"loss": 3.5338,
"step": 1154560
},
{
"epoch": 1.0,
"learning_rate": 3.108954095454358e-05,
"loss": 3.5532,
"step": 1155072
},
{
"epoch": 1.0,
"learning_rate": 3.108117138583679e-05,
"loss": 3.5444,
"step": 1155584
},
{
"epoch": 1.0,
"learning_rate": 3.1072785438326266e-05,
"loss": 3.5439,
"step": 1156096
},
{
"epoch": 1.0,
"learning_rate": 3.1064399490815746e-05,
"loss": 3.5435,
"step": 1156608
},
{
"epoch": 1.0,
"learning_rate": 3.1056013543305226e-05,
"loss": 3.5533,
"step": 1157120
},
{
"epoch": 1.0,
"learning_rate": 3.104764397459844e-05,
"loss": 3.5349,
"step": 1157632
},
{
"epoch": 1.0,
"learning_rate": 3.103925802708792e-05,
"loss": 3.5333,
"step": 1158144
},
{
"epoch": 1.0,
"learning_rate": 3.10308720795774e-05,
"loss": 3.5509,
"step": 1158656
},
{
"epoch": 1.0,
"learning_rate": 3.102248613206688e-05,
"loss": 3.5336,
"step": 1159168
},
{
"epoch": 1.0,
"learning_rate": 3.10141165633601e-05,
"loss": 3.5224,
"step": 1159680
},
{
"epoch": 1.01,
"learning_rate": 3.100573061584957e-05,
"loss": 3.5385,
"step": 1160192
},
{
"epoch": 1.01,
"learning_rate": 3.099734466833905e-05,
"loss": 3.542,
"step": 1160704
},
{
"epoch": 1.01,
"learning_rate": 3.098895872082853e-05,
"loss": 3.5465,
"step": 1161216
},
{
"epoch": 1.01,
"learning_rate": 3.098058915212174e-05,
"loss": 3.5422,
"step": 1161728
},
{
"epoch": 1.01,
"learning_rate": 3.097220320461122e-05,
"loss": 3.5386,
"step": 1162240
},
{
"epoch": 1.01,
"learning_rate": 3.09638172571007e-05,
"loss": 3.5429,
"step": 1162752
},
{
"epoch": 1.01,
"learning_rate": 3.095543130959018e-05,
"loss": 3.5464,
"step": 1163264
},
{
"epoch": 1.01,
"learning_rate": 3.0947061740883395e-05,
"loss": 3.5279,
"step": 1163776
},
{
"epoch": 1.01,
"learning_rate": 3.0938675793372875e-05,
"loss": 3.5425,
"step": 1164288
},
{
"epoch": 1.01,
"learning_rate": 3.0930289845862355e-05,
"loss": 3.5257,
"step": 1164800
},
{
"epoch": 1.01,
"learning_rate": 3.0921903898351835e-05,
"loss": 3.5317,
"step": 1165312
},
{
"epoch": 1.01,
"learning_rate": 3.0913534329645044e-05,
"loss": 3.5359,
"step": 1165824
},
{
"epoch": 1.01,
"learning_rate": 3.0905148382134524e-05,
"loss": 3.5482,
"step": 1166336
},
{
"epoch": 1.01,
"learning_rate": 3.0896762434624004e-05,
"loss": 3.5402,
"step": 1166848
},
{
"epoch": 1.01,
"learning_rate": 3.0888376487113484e-05,
"loss": 3.5376,
"step": 1167360
},
{
"epoch": 1.01,
"learning_rate": 3.0879990539602964e-05,
"loss": 3.5432,
"step": 1167872
},
{
"epoch": 1.01,
"learning_rate": 3.087162097089617e-05,
"loss": 3.5365,
"step": 1168384
},
{
"epoch": 1.01,
"learning_rate": 3.086323502338565e-05,
"loss": 3.5449,
"step": 1168896
},
{
"epoch": 1.01,
"learning_rate": 3.085484907587513e-05,
"loss": 3.5155,
"step": 1169408
},
{
"epoch": 1.01,
"learning_rate": 3.084646312836461e-05,
"loss": 3.5453,
"step": 1169920
},
{
"epoch": 1.01,
"learning_rate": 3.083809355965783e-05,
"loss": 3.5398,
"step": 1170432
},
{
"epoch": 1.01,
"learning_rate": 3.082970761214731e-05,
"loss": 3.544,
"step": 1170944
},
{
"epoch": 1.01,
"learning_rate": 3.082132166463679e-05,
"loss": 3.5379,
"step": 1171456
},
{
"epoch": 1.01,
"learning_rate": 3.081293571712627e-05,
"loss": 3.5319,
"step": 1171968
},
{
"epoch": 1.01,
"learning_rate": 3.080456614841948e-05,
"loss": 3.5206,
"step": 1172480
},
{
"epoch": 1.01,
"learning_rate": 3.079618020090896e-05,
"loss": 3.5223,
"step": 1172992
},
{
"epoch": 1.01,
"learning_rate": 3.078779425339844e-05,
"loss": 3.5457,
"step": 1173504
},
{
"epoch": 1.01,
"learning_rate": 3.077940830588792e-05,
"loss": 3.5255,
"step": 1174016
},
{
"epoch": 1.01,
"learning_rate": 3.077103873718113e-05,
"loss": 3.5464,
"step": 1174528
},
{
"epoch": 1.01,
"learning_rate": 3.076265278967061e-05,
"loss": 3.5367,
"step": 1175040
},
{
"epoch": 1.01,
"learning_rate": 3.075426684216009e-05,
"loss": 3.5239,
"step": 1175552
},
{
"epoch": 1.01,
"learning_rate": 3.074588089464957e-05,
"loss": 3.5385,
"step": 1176064
},
{
"epoch": 1.01,
"learning_rate": 3.073751132594278e-05,
"loss": 3.5212,
"step": 1176576
},
{
"epoch": 1.01,
"learning_rate": 3.072912537843226e-05,
"loss": 3.5276,
"step": 1177088
},
{
"epoch": 1.01,
"learning_rate": 3.072073943092174e-05,
"loss": 3.5311,
"step": 1177600
},
{
"epoch": 1.01,
"learning_rate": 3.071235348341122e-05,
"loss": 3.5415,
"step": 1178112
},
{
"epoch": 1.01,
"learning_rate": 3.070398391470443e-05,
"loss": 3.5196,
"step": 1178624
},
{
"epoch": 1.01,
"learning_rate": 3.069559796719391e-05,
"loss": 3.5241,
"step": 1179136
},
{
"epoch": 1.01,
"learning_rate": 3.068721201968339e-05,
"loss": 3.5174,
"step": 1179648
},
{
"epoch": 1.01,
"learning_rate": 3.067882607217287e-05,
"loss": 3.5279,
"step": 1180160
},
{
"epoch": 1.01,
"learning_rate": 3.067044012466235e-05,
"loss": 3.5387,
"step": 1180672
},
{
"epoch": 1.01,
"learning_rate": 3.066207055595556e-05,
"loss": 3.5385,
"step": 1181184
},
{
"epoch": 1.01,
"learning_rate": 3.065368460844504e-05,
"loss": 3.5361,
"step": 1181696
},
{
"epoch": 1.01,
"learning_rate": 3.064529866093452e-05,
"loss": 3.5362,
"step": 1182208
},
{
"epoch": 1.01,
"learning_rate": 3.063691271342401e-05,
"loss": 3.547,
"step": 1182720
},
{
"epoch": 1.01,
"learning_rate": 3.0628543144717216e-05,
"loss": 3.5299,
"step": 1183232
},
{
"epoch": 1.01,
"learning_rate": 3.0620157197206696e-05,
"loss": 3.5358,
"step": 1183744
},
{
"epoch": 1.01,
"learning_rate": 3.0611771249696176e-05,
"loss": 3.531,
"step": 1184256
},
{
"epoch": 1.01,
"learning_rate": 3.0603401680989385e-05,
"loss": 3.527,
"step": 1184768
},
{
"epoch": 1.01,
"learning_rate": 3.0595015733478865e-05,
"loss": 3.5343,
"step": 1185280
},
{
"epoch": 1.01,
"learning_rate": 3.0586629785968345e-05,
"loss": 3.531,
"step": 1185792
},
{
"epoch": 1.01,
"learning_rate": 3.0578243838457825e-05,
"loss": 3.5428,
"step": 1186304
},
{
"epoch": 1.01,
"learning_rate": 3.0569874269751034e-05,
"loss": 3.5403,
"step": 1186816
},
{
"epoch": 1.01,
"learning_rate": 3.0561488322240514e-05,
"loss": 3.5299,
"step": 1187328
},
{
"epoch": 1.01,
"learning_rate": 3.0553102374729994e-05,
"loss": 3.5164,
"step": 1187840
},
{
"epoch": 1.01,
"learning_rate": 3.0544716427219474e-05,
"loss": 3.5287,
"step": 1188352
},
{
"epoch": 1.01,
"learning_rate": 3.053634685851269e-05,
"loss": 3.5354,
"step": 1188864
},
{
"epoch": 1.01,
"learning_rate": 3.052796091100217e-05,
"loss": 3.5321,
"step": 1189376
},
{
"epoch": 1.01,
"learning_rate": 3.051957496349165e-05,
"loss": 3.5332,
"step": 1189888
},
{
"epoch": 1.01,
"learning_rate": 3.051118901598113e-05,
"loss": 3.5394,
"step": 1190400
},
{
"epoch": 1.02,
"learning_rate": 3.050280306847061e-05,
"loss": 3.534,
"step": 1190912
},
{
"epoch": 1.02,
"learning_rate": 3.049443349976382e-05,
"loss": 3.5258,
"step": 1191424
},
{
"epoch": 1.02,
"learning_rate": 3.04860475522533e-05,
"loss": 3.5257,
"step": 1191936
},
{
"epoch": 1.02,
"learning_rate": 3.047766160474278e-05,
"loss": 3.5388,
"step": 1192448
},
{
"epoch": 1.02,
"learning_rate": 3.046927565723226e-05,
"loss": 3.5405,
"step": 1192960
},
{
"epoch": 1.02,
"learning_rate": 3.046090608852547e-05,
"loss": 3.5385,
"step": 1193472
},
{
"epoch": 1.02,
"learning_rate": 3.045252014101495e-05,
"loss": 3.5278,
"step": 1193984
},
{
"epoch": 1.02,
"learning_rate": 3.044413419350443e-05,
"loss": 3.5271,
"step": 1194496
},
{
"epoch": 1.02,
"learning_rate": 3.043574824599391e-05,
"loss": 3.5407,
"step": 1195008
},
{
"epoch": 1.02,
"learning_rate": 3.042737867728712e-05,
"loss": 3.5356,
"step": 1195520
},
{
"epoch": 1.02,
"learning_rate": 3.04189927297766e-05,
"loss": 3.5349,
"step": 1196032
},
{
"epoch": 1.02,
"learning_rate": 3.0410606782266084e-05,
"loss": 3.5281,
"step": 1196544
},
{
"epoch": 1.02,
"learning_rate": 3.0402220834755564e-05,
"loss": 3.5272,
"step": 1197056
},
{
"epoch": 1.02,
"learning_rate": 3.0393851266048773e-05,
"loss": 3.5331,
"step": 1197568
},
{
"epoch": 1.02,
"learning_rate": 3.0385465318538253e-05,
"loss": 3.5325,
"step": 1198080
},
{
"epoch": 1.02,
"learning_rate": 3.0377079371027733e-05,
"loss": 3.5193,
"step": 1198592
},
{
"epoch": 1.02,
"learning_rate": 3.0368693423517213e-05,
"loss": 3.5253,
"step": 1199104
},
{
"epoch": 1.02,
"learning_rate": 3.0360323854810425e-05,
"loss": 3.5322,
"step": 1199616
},
{
"epoch": 1.02,
"learning_rate": 3.0351937907299905e-05,
"loss": 3.5342,
"step": 1200128
},
{
"epoch": 1.02,
"learning_rate": 3.0343551959789385e-05,
"loss": 3.5228,
"step": 1200640
},
{
"epoch": 1.02,
"learning_rate": 3.0335166012278865e-05,
"loss": 3.5365,
"step": 1201152
},
{
"epoch": 1.02,
"learning_rate": 3.0326796443572074e-05,
"loss": 3.5184,
"step": 1201664
},
{
"epoch": 1.02,
"learning_rate": 3.0318410496061554e-05,
"loss": 3.544,
"step": 1202176
},
{
"epoch": 1.02,
"learning_rate": 3.0310024548551037e-05,
"loss": 3.5221,
"step": 1202688
},
{
"epoch": 1.02,
"learning_rate": 3.0301638601040517e-05,
"loss": 3.533,
"step": 1203200
},
{
"epoch": 1.02,
"learning_rate": 3.0293269032333726e-05,
"loss": 3.5367,
"step": 1203712
},
{
"epoch": 1.02,
"learning_rate": 3.0284883084823206e-05,
"loss": 3.5416,
"step": 1204224
},
{
"epoch": 1.02,
"learning_rate": 3.0276497137312686e-05,
"loss": 3.5255,
"step": 1204736
},
{
"epoch": 1.02,
"learning_rate": 3.0268111189802166e-05,
"loss": 3.5264,
"step": 1205248
},
{
"epoch": 1.02,
"learning_rate": 3.025974162109538e-05,
"loss": 3.5364,
"step": 1205760
},
{
"epoch": 1.02,
"learning_rate": 3.025135567358486e-05,
"loss": 3.5329,
"step": 1206272
},
{
"epoch": 1.02,
"learning_rate": 3.024296972607434e-05,
"loss": 3.5221,
"step": 1206784
},
{
"epoch": 1.02,
"learning_rate": 3.023458377856382e-05,
"loss": 3.5248,
"step": 1207296
},
{
"epoch": 1.02,
"learning_rate": 3.0226214209857028e-05,
"loss": 3.5281,
"step": 1207808
},
{
"epoch": 1.02,
"learning_rate": 3.0217828262346508e-05,
"loss": 3.5369,
"step": 1208320
},
{
"epoch": 1.02,
"learning_rate": 3.020944231483599e-05,
"loss": 3.5264,
"step": 1208832
},
{
"epoch": 1.02,
"learning_rate": 3.020105636732547e-05,
"loss": 3.5252,
"step": 1209344
},
{
"epoch": 1.02,
"learning_rate": 3.019268679861868e-05,
"loss": 3.5301,
"step": 1209856
},
{
"epoch": 1.02,
"learning_rate": 3.018430085110816e-05,
"loss": 3.526,
"step": 1210368
},
{
"epoch": 1.02,
"learning_rate": 3.017591490359764e-05,
"loss": 3.5248,
"step": 1210880
},
{
"epoch": 1.02,
"learning_rate": 3.016752895608712e-05,
"loss": 3.5398,
"step": 1211392
},
{
"epoch": 1.02,
"learning_rate": 3.0159159387380332e-05,
"loss": 3.5417,
"step": 1211904
},
{
"epoch": 1.02,
"learning_rate": 3.0150773439869812e-05,
"loss": 3.5252,
"step": 1212416
},
{
"epoch": 1.02,
"learning_rate": 3.0142387492359292e-05,
"loss": 3.5275,
"step": 1212928
},
{
"epoch": 1.02,
"learning_rate": 3.0134001544848765e-05,
"loss": 3.54,
"step": 1213440
},
{
"epoch": 1.02,
"learning_rate": 3.012563197614198e-05,
"loss": 3.5321,
"step": 1213952
},
{
"epoch": 1.02,
"learning_rate": 3.011724602863146e-05,
"loss": 3.5316,
"step": 1214464
},
{
"epoch": 1.02,
"learning_rate": 3.0108860081120945e-05,
"loss": 3.5222,
"step": 1214976
},
{
"epoch": 1.02,
"learning_rate": 3.0100474133610418e-05,
"loss": 3.544,
"step": 1215488
},
{
"epoch": 1.02,
"learning_rate": 3.0092104564903634e-05,
"loss": 3.536,
"step": 1216000
},
{
"epoch": 1.02,
"learning_rate": 3.0083718617393114e-05,
"loss": 3.5409,
"step": 1216512
},
{
"epoch": 1.02,
"learning_rate": 3.0075332669882594e-05,
"loss": 3.5284,
"step": 1217024
},
{
"epoch": 1.02,
"learning_rate": 3.006694672237207e-05,
"loss": 3.5408,
"step": 1217536
},
{
"epoch": 1.02,
"learning_rate": 3.0058577153665286e-05,
"loss": 3.5312,
"step": 1218048
},
{
"epoch": 1.02,
"learning_rate": 3.0050191206154766e-05,
"loss": 3.5189,
"step": 1218560
},
{
"epoch": 1.02,
"learning_rate": 3.004180525864424e-05,
"loss": 3.5445,
"step": 1219072
},
{
"epoch": 1.02,
"learning_rate": 3.003341931113372e-05,
"loss": 3.5325,
"step": 1219584
},
{
"epoch": 1.02,
"learning_rate": 3.0025049742426935e-05,
"loss": 3.54,
"step": 1220096
},
{
"epoch": 1.02,
"learning_rate": 3.0016663794916415e-05,
"loss": 3.5264,
"step": 1220608
},
{
"epoch": 1.03,
"learning_rate": 3.000827784740589e-05,
"loss": 3.528,
"step": 1221120
},
{
"epoch": 1.03,
"eval_loss": 3.8475143909454346,
"eval_runtime": 304.4889,
"eval_samples_per_second": 1253.218,
"eval_steps_per_second": 39.164,
"step": 1221120
},
{
"epoch": 0.0,
"learning_rate": 2.999989189989537e-05,
"loss": 3.515,
"step": 1221632
},
{
"epoch": 0.0,
"learning_rate": 2.999150595238485e-05,
"loss": 3.522,
"step": 1222144
},
{
"epoch": 0.0,
"learning_rate": 2.998312000487433e-05,
"loss": 3.5405,
"step": 1222656
},
{
"epoch": 0.0,
"learning_rate": 2.997473405736381e-05,
"loss": 3.53,
"step": 1223168
},
{
"epoch": 0.0,
"learning_rate": 2.9966364488657024e-05,
"loss": 3.5366,
"step": 1223680
},
{
"epoch": 0.0,
"learning_rate": 2.9957978541146504e-05,
"loss": 3.5248,
"step": 1224192
},
{
"epoch": 0.0,
"learning_rate": 2.9949592593635984e-05,
"loss": 3.5224,
"step": 1224704
},
{
"epoch": 0.0,
"learning_rate": 2.9941206646125464e-05,
"loss": 3.5156,
"step": 1225216
},
{
"epoch": 0.0,
"learning_rate": 2.9932837077418673e-05,
"loss": 3.5298,
"step": 1225728
},
{
"epoch": 0.0,
"learning_rate": 2.9924451129908153e-05,
"loss": 3.5264,
"step": 1226240
},
{
"epoch": 0.0,
"learning_rate": 2.9916065182397636e-05,
"loss": 3.5389,
"step": 1226752
},
{
"epoch": 0.0,
"learning_rate": 2.9907695613690845e-05,
"loss": 3.5422,
"step": 1227264
},
{
"epoch": 0.0,
"learning_rate": 2.9899309666180325e-05,
"loss": 3.5205,
"step": 1227776
},
{
"epoch": 0.0,
"learning_rate": 2.9890923718669805e-05,
"loss": 3.5217,
"step": 1228288
},
{
"epoch": 0.0,
"learning_rate": 2.9882537771159285e-05,
"loss": 3.5104,
"step": 1228800
},
{
"epoch": 0.0,
"learning_rate": 2.9874151823648765e-05,
"loss": 3.5156,
"step": 1229312
},
{
"epoch": 0.0,
"learning_rate": 2.9865765876138245e-05,
"loss": 3.5254,
"step": 1229824
},
{
"epoch": 0.0,
"learning_rate": 2.985737992862773e-05,
"loss": 3.5244,
"step": 1230336
},
{
"epoch": 0.0,
"learning_rate": 2.9848993981117208e-05,
"loss": 3.5188,
"step": 1230848
},
{
"epoch": 0.0,
"learning_rate": 2.9840608033606688e-05,
"loss": 3.5377,
"step": 1231360
},
{
"epoch": 0.0,
"learning_rate": 2.9832238464899897e-05,
"loss": 3.5312,
"step": 1231872
},
{
"epoch": 0.0,
"learning_rate": 2.9823852517389377e-05,
"loss": 3.5286,
"step": 1232384
},
{
"epoch": 0.0,
"learning_rate": 2.9815466569878857e-05,
"loss": 3.5301,
"step": 1232896
},
{
"epoch": 0.0,
"learning_rate": 2.9807080622368337e-05,
"loss": 3.542,
"step": 1233408
},
{
"epoch": 0.0,
"learning_rate": 2.979871105366155e-05,
"loss": 3.5178,
"step": 1233920
},
{
"epoch": 0.0,
"learning_rate": 2.979032510615103e-05,
"loss": 3.5211,
"step": 1234432
},
{
"epoch": 0.0,
"learning_rate": 2.978193915864051e-05,
"loss": 3.5392,
"step": 1234944
},
{
"epoch": 0.0,
"learning_rate": 2.977355321112999e-05,
"loss": 3.516,
"step": 1235456
},
{
"epoch": 0.0,
"learning_rate": 2.97651836424232e-05,
"loss": 3.5148,
"step": 1235968
},
{
"epoch": 0.01,
"learning_rate": 2.9756797694912682e-05,
"loss": 3.5202,
"step": 1236480
},
{
"epoch": 0.01,
"learning_rate": 2.9748411747402162e-05,
"loss": 3.5286,
"step": 1236992
},
{
"epoch": 0.01,
"learning_rate": 2.9740025799891642e-05,
"loss": 3.531,
"step": 1237504
},
{
"epoch": 0.01,
"learning_rate": 2.973165623118485e-05,
"loss": 3.527,
"step": 1238016
},
{
"epoch": 0.01,
"learning_rate": 2.972327028367433e-05,
"loss": 3.5249,
"step": 1238528
},
{
"epoch": 0.01,
"learning_rate": 2.971488433616381e-05,
"loss": 3.5294,
"step": 1239040
},
{
"epoch": 0.01,
"learning_rate": 2.970649838865329e-05,
"loss": 3.5285,
"step": 1239552
},
{
"epoch": 0.01,
"learning_rate": 2.9698128819946503e-05,
"loss": 3.5184,
"step": 1240064
},
{
"epoch": 0.01,
"learning_rate": 2.9689742872435983e-05,
"loss": 3.5272,
"step": 1240576
},
{
"epoch": 0.01,
"learning_rate": 2.9681356924925463e-05,
"loss": 3.5091,
"step": 1241088
},
{
"epoch": 0.01,
"learning_rate": 2.9672970977414943e-05,
"loss": 3.5207,
"step": 1241600
},
{
"epoch": 0.01,
"learning_rate": 2.9664601408708152e-05,
"loss": 3.5196,
"step": 1242112
},
{
"epoch": 0.01,
"learning_rate": 2.9656215461197632e-05,
"loss": 3.5353,
"step": 1242624
},
{
"epoch": 0.01,
"learning_rate": 2.9647829513687116e-05,
"loss": 3.5252,
"step": 1243136
},
{
"epoch": 0.01,
"learning_rate": 2.9639443566176596e-05,
"loss": 3.5242,
"step": 1243648
},
{
"epoch": 0.01,
"learning_rate": 2.9631073997469805e-05,
"loss": 3.5273,
"step": 1244160
},
{
"epoch": 0.01,
"learning_rate": 2.9622688049959285e-05,
"loss": 3.5259,
"step": 1244672
},
{
"epoch": 0.01,
"learning_rate": 2.9614302102448765e-05,
"loss": 3.5293,
"step": 1245184
},
{
"epoch": 0.01,
"learning_rate": 2.9605916154938245e-05,
"loss": 3.502,
"step": 1245696
},
{
"epoch": 0.01,
"learning_rate": 2.9597546586231457e-05,
"loss": 3.5278,
"step": 1246208
},
{
"epoch": 0.01,
"learning_rate": 2.9589160638720937e-05,
"loss": 3.5289,
"step": 1246720
},
{
"epoch": 0.01,
"learning_rate": 2.9580774691210417e-05,
"loss": 3.5285,
"step": 1247232
},
{
"epoch": 0.01,
"learning_rate": 2.9572388743699897e-05,
"loss": 3.5193,
"step": 1247744
},
{
"epoch": 0.01,
"learning_rate": 2.9564019174993106e-05,
"loss": 3.5178,
"step": 1248256
},
{
"epoch": 0.01,
"learning_rate": 2.9555633227482586e-05,
"loss": 3.5079,
"step": 1248768
},
{
"epoch": 0.01,
"learning_rate": 2.954724727997207e-05,
"loss": 3.5095,
"step": 1249280
},
{
"epoch": 0.01,
"learning_rate": 2.953886133246155e-05,
"loss": 3.5321,
"step": 1249792
},
{
"epoch": 0.01,
"learning_rate": 2.953049176375476e-05,
"loss": 3.5105,
"step": 1250304
},
{
"epoch": 0.01,
"learning_rate": 2.9522105816244238e-05,
"loss": 3.5311,
"step": 1250816
},
{
"epoch": 0.01,
"learning_rate": 2.9513719868733718e-05,
"loss": 3.5242,
"step": 1251328
},
{
"epoch": 0.01,
"learning_rate": 2.9505333921223198e-05,
"loss": 3.5097,
"step": 1251840
},
{
"epoch": 0.01,
"learning_rate": 2.949696435251641e-05,
"loss": 3.5227,
"step": 1252352
},
{
"epoch": 0.01,
"learning_rate": 2.948857840500589e-05,
"loss": 3.5109,
"step": 1252864
},
{
"epoch": 0.01,
"learning_rate": 2.948019245749537e-05,
"loss": 3.5138,
"step": 1253376
},
{
"epoch": 0.01,
"learning_rate": 2.9471806509984844e-05,
"loss": 3.5145,
"step": 1253888
},
{
"epoch": 0.01,
"learning_rate": 2.946343694127806e-05,
"loss": 3.5298,
"step": 1254400
},
{
"epoch": 0.01,
"learning_rate": 2.945505099376754e-05,
"loss": 3.5069,
"step": 1254912
},
{
"epoch": 0.01,
"learning_rate": 2.9446665046257023e-05,
"loss": 3.5084,
"step": 1255424
},
{
"epoch": 0.01,
"learning_rate": 2.9438279098746496e-05,
"loss": 3.5035,
"step": 1255936
},
{
"epoch": 0.01,
"learning_rate": 2.9429909530039712e-05,
"loss": 3.5156,
"step": 1256448
},
{
"epoch": 0.01,
"learning_rate": 2.9421523582529192e-05,
"loss": 3.5209,
"step": 1256960
},
{
"epoch": 0.01,
"learning_rate": 2.9413137635018672e-05,
"loss": 3.527,
"step": 1257472
},
{
"epoch": 0.01,
"learning_rate": 2.940475168750815e-05,
"loss": 3.5193,
"step": 1257984
},
{
"epoch": 0.01,
"learning_rate": 2.9396382118801364e-05,
"loss": 3.5266,
"step": 1258496
},
{
"epoch": 0.01,
"learning_rate": 2.9387996171290844e-05,
"loss": 3.5316,
"step": 1259008
},
{
"epoch": 0.01,
"learning_rate": 2.9379610223780317e-05,
"loss": 3.5176,
"step": 1259520
},
{
"epoch": 0.01,
"learning_rate": 2.9371224276269797e-05,
"loss": 3.5214,
"step": 1260032
},
{
"epoch": 0.01,
"learning_rate": 2.9362854707563013e-05,
"loss": 3.5142,
"step": 1260544
},
{
"epoch": 0.01,
"learning_rate": 2.9354468760052493e-05,
"loss": 3.5153,
"step": 1261056
},
{
"epoch": 0.01,
"learning_rate": 2.934608281254197e-05,
"loss": 3.5231,
"step": 1261568
},
{
"epoch": 0.01,
"learning_rate": 2.933769686503145e-05,
"loss": 3.5113,
"step": 1262080
},
{
"epoch": 0.01,
"learning_rate": 2.9329327296324666e-05,
"loss": 3.5307,
"step": 1262592
},
{
"epoch": 0.01,
"learning_rate": 2.9320941348814146e-05,
"loss": 3.5288,
"step": 1263104
},
{
"epoch": 0.01,
"learning_rate": 2.9312555401303622e-05,
"loss": 3.5155,
"step": 1263616
},
{
"epoch": 0.01,
"learning_rate": 2.9304169453793102e-05,
"loss": 3.5035,
"step": 1264128
},
{
"epoch": 0.01,
"learning_rate": 2.9295799885086318e-05,
"loss": 3.5117,
"step": 1264640
},
{
"epoch": 0.01,
"learning_rate": 2.928741393757579e-05,
"loss": 3.5199,
"step": 1265152
},
{
"epoch": 0.01,
"learning_rate": 2.927902799006527e-05,
"loss": 3.5219,
"step": 1265664
},
{
"epoch": 0.01,
"learning_rate": 2.927064204255475e-05,
"loss": 3.5172,
"step": 1266176
},
{
"epoch": 0.01,
"learning_rate": 2.9262272473847967e-05,
"loss": 3.5247,
"step": 1266688
},
{
"epoch": 0.02,
"learning_rate": 2.9253886526337444e-05,
"loss": 3.5204,
"step": 1267200
},
{
"epoch": 0.02,
"learning_rate": 2.9245500578826923e-05,
"loss": 3.5073,
"step": 1267712
},
{
"epoch": 0.02,
"learning_rate": 2.9237114631316403e-05,
"loss": 3.5082,
"step": 1268224
},
{
"epoch": 0.02,
"learning_rate": 2.922874506260962e-05,
"loss": 3.5264,
"step": 1268736
},
{
"epoch": 0.02,
"learning_rate": 2.9220359115099093e-05,
"loss": 3.5226,
"step": 1269248
},
{
"epoch": 0.02,
"learning_rate": 2.9211973167588576e-05,
"loss": 3.5285,
"step": 1269760
},
{
"epoch": 0.02,
"learning_rate": 2.9203587220078056e-05,
"loss": 3.5095,
"step": 1270272
},
{
"epoch": 0.02,
"learning_rate": 2.9195217651371265e-05,
"loss": 3.515,
"step": 1270784
},
{
"epoch": 0.02,
"learning_rate": 2.9186831703860745e-05,
"loss": 3.5263,
"step": 1271296
},
{
"epoch": 0.02,
"learning_rate": 2.9178445756350225e-05,
"loss": 3.5235,
"step": 1271808
},
{
"epoch": 0.02,
"learning_rate": 2.9170059808839705e-05,
"loss": 3.518,
"step": 1272320
},
{
"epoch": 0.02,
"learning_rate": 2.9161690240132917e-05,
"loss": 3.519,
"step": 1272832
},
{
"epoch": 0.02,
"learning_rate": 2.9153304292622397e-05,
"loss": 3.5113,
"step": 1273344
},
{
"epoch": 0.02,
"learning_rate": 2.9144918345111877e-05,
"loss": 3.5164,
"step": 1273856
},
{
"epoch": 0.02,
"learning_rate": 2.9136532397601357e-05,
"loss": 3.5223,
"step": 1274368
},
{
"epoch": 0.02,
"learning_rate": 2.9128162828894566e-05,
"loss": 3.5022,
"step": 1274880
},
{
"epoch": 0.02,
"learning_rate": 2.9119776881384046e-05,
"loss": 3.514,
"step": 1275392
},
{
"epoch": 0.02,
"learning_rate": 2.911139093387353e-05,
"loss": 3.5207,
"step": 1275904
},
{
"epoch": 0.02,
"learning_rate": 2.910300498636301e-05,
"loss": 3.5219,
"step": 1276416
},
{
"epoch": 0.02,
"learning_rate": 2.909463541765622e-05,
"loss": 3.5052,
"step": 1276928
},
{
"epoch": 0.02,
"learning_rate": 2.90862494701457e-05,
"loss": 3.5238,
"step": 1277440
},
{
"epoch": 0.02,
"learning_rate": 2.907786352263518e-05,
"loss": 3.5069,
"step": 1277952
},
{
"epoch": 0.02,
"learning_rate": 2.906947757512466e-05,
"loss": 3.5316,
"step": 1278464
},
{
"epoch": 0.02,
"learning_rate": 2.906110800641787e-05,
"loss": 3.5045,
"step": 1278976
},
{
"epoch": 0.02,
"learning_rate": 2.905272205890735e-05,
"loss": 3.5185,
"step": 1279488
},
{
"epoch": 0.02,
"learning_rate": 2.904433611139683e-05,
"loss": 3.5209,
"step": 1280000
},
{
"epoch": 0.02,
"learning_rate": 2.903595016388631e-05,
"loss": 3.5293,
"step": 1280512
},
{
"epoch": 0.02,
"learning_rate": 2.902758059517952e-05,
"loss": 3.5124,
"step": 1281024
},
{
"epoch": 0.02,
"learning_rate": 2.9019194647669e-05,
"loss": 3.5145,
"step": 1281536
},
{
"epoch": 0.02,
"learning_rate": 2.9010808700158483e-05,
"loss": 3.5193,
"step": 1282048
},
{
"epoch": 0.02,
"learning_rate": 2.9002422752647963e-05,
"loss": 3.5171,
"step": 1282560
},
{
"epoch": 0.02,
"learning_rate": 2.8994053183941172e-05,
"loss": 3.5096,
"step": 1283072
},
{
"epoch": 0.02,
"learning_rate": 2.8985667236430652e-05,
"loss": 3.5129,
"step": 1283584
},
{
"epoch": 0.02,
"learning_rate": 2.8977281288920132e-05,
"loss": 3.51,
"step": 1284096
},
{
"epoch": 0.02,
"learning_rate": 2.8968895341409612e-05,
"loss": 3.5301,
"step": 1284608
},
{
"epoch": 0.02,
"learning_rate": 2.8960525772702825e-05,
"loss": 3.5077,
"step": 1285120
},
{
"epoch": 0.02,
"learning_rate": 2.8952139825192305e-05,
"loss": 3.5137,
"step": 1285632
},
{
"epoch": 0.02,
"learning_rate": 2.8943753877681784e-05,
"loss": 3.5136,
"step": 1286144
},
{
"epoch": 0.02,
"learning_rate": 2.8935367930171264e-05,
"loss": 3.5147,
"step": 1286656
},
{
"epoch": 0.02,
"learning_rate": 2.8926998361464474e-05,
"loss": 3.5119,
"step": 1287168
},
{
"epoch": 0.02,
"learning_rate": 2.8918612413953954e-05,
"loss": 3.5275,
"step": 1287680
},
{
"epoch": 0.02,
"learning_rate": 2.8910226466443437e-05,
"loss": 3.5261,
"step": 1288192
},
{
"epoch": 0.02,
"learning_rate": 2.8901840518932917e-05,
"loss": 3.5165,
"step": 1288704
},
{
"epoch": 0.02,
"learning_rate": 2.8893470950226126e-05,
"loss": 3.5097,
"step": 1289216
},
{
"epoch": 0.02,
"learning_rate": 2.8885085002715606e-05,
"loss": 3.5214,
"step": 1289728
},
{
"epoch": 0.02,
"learning_rate": 2.8876699055205086e-05,
"loss": 3.521,
"step": 1290240
},
{
"epoch": 0.02,
"learning_rate": 2.8868313107694566e-05,
"loss": 3.5221,
"step": 1290752
},
{
"epoch": 0.02,
"learning_rate": 2.8859943538987778e-05,
"loss": 3.5085,
"step": 1291264
},
{
"epoch": 0.02,
"learning_rate": 2.8851557591477258e-05,
"loss": 3.5311,
"step": 1291776
},
{
"epoch": 0.02,
"learning_rate": 2.8843171643966738e-05,
"loss": 3.5189,
"step": 1292288
},
{
"epoch": 0.02,
"learning_rate": 2.8834785696456218e-05,
"loss": 3.5303,
"step": 1292800
},
{
"epoch": 0.02,
"learning_rate": 2.8826416127749427e-05,
"loss": 3.514,
"step": 1293312
},
{
"epoch": 0.02,
"learning_rate": 2.8818030180238907e-05,
"loss": 3.5291,
"step": 1293824
},
{
"epoch": 0.02,
"learning_rate": 2.880964423272839e-05,
"loss": 3.5188,
"step": 1294336
},
{
"epoch": 0.02,
"learning_rate": 2.880125828521787e-05,
"loss": 3.5008,
"step": 1294848
},
{
"epoch": 0.02,
"learning_rate": 2.879288871651108e-05,
"loss": 3.5343,
"step": 1295360
},
{
"epoch": 0.02,
"learning_rate": 2.878450276900056e-05,
"loss": 3.5193,
"step": 1295872
},
{
"epoch": 0.02,
"learning_rate": 2.877611682149004e-05,
"loss": 3.5216,
"step": 1296384
},
{
"epoch": 0.02,
"learning_rate": 2.876773087397952e-05,
"loss": 3.5152,
"step": 1296896
},
{
"epoch": 0.02,
"learning_rate": 2.8759361305272732e-05,
"loss": 3.5125,
"step": 1297408
},
{
"epoch": 0.03,
"eval_loss": 3.84833025932312,
"eval_runtime": 371.1811,
"eval_samples_per_second": 1028.045,
"eval_steps_per_second": 32.127,
"step": 1297440
},
{
"epoch": 0.0,
"learning_rate": 2.8750975357762212e-05,
"loss": 3.503,
"step": 1297920
},
{
"epoch": 0.0,
"learning_rate": 2.8742589410251692e-05,
"loss": 3.5095,
"step": 1298432
},
{
"epoch": 0.0,
"learning_rate": 2.8734203462741172e-05,
"loss": 3.5256,
"step": 1298944
},
{
"epoch": 0.0,
"learning_rate": 2.872583389403438e-05,
"loss": 3.5126,
"step": 1299456
},
{
"epoch": 0.0,
"learning_rate": 2.871744794652386e-05,
"loss": 3.5227,
"step": 1299968
},
{
"epoch": 0.0,
"learning_rate": 2.870906199901334e-05,
"loss": 3.5137,
"step": 1300480
},
{
"epoch": 0.0,
"learning_rate": 2.8700676051502824e-05,
"loss": 3.5083,
"step": 1300992
},
{
"epoch": 0.0,
"learning_rate": 2.8692306482796033e-05,
"loss": 3.5043,
"step": 1301504
},
{
"epoch": 0.0,
"learning_rate": 2.8683920535285513e-05,
"loss": 3.5138,
"step": 1302016
},
{
"epoch": 0.0,
"learning_rate": 2.8675534587774993e-05,
"loss": 3.5139,
"step": 1302528
},
{
"epoch": 0.0,
"learning_rate": 2.8667148640264473e-05,
"loss": 3.5246,
"step": 1303040
},
{
"epoch": 0.0,
"learning_rate": 2.8658779071557686e-05,
"loss": 3.523,
"step": 1303552
},
{
"epoch": 0.0,
"learning_rate": 2.8650409502850895e-05,
"loss": 3.5138,
"step": 1304064
},
{
"epoch": 0.0,
"learning_rate": 2.8642023555340375e-05,
"loss": 3.5052,
"step": 1304576
},
{
"epoch": 0.0,
"learning_rate": 2.8633637607829855e-05,
"loss": 3.501,
"step": 1305088
},
{
"epoch": 0.0,
"learning_rate": 2.8625251660319335e-05,
"loss": 3.5007,
"step": 1305600
},
{
"epoch": 0.0,
"learning_rate": 2.8616865712808815e-05,
"loss": 3.512,
"step": 1306112
},
{
"epoch": 0.0,
"learning_rate": 2.8608479765298294e-05,
"loss": 3.5113,
"step": 1306624
},
{
"epoch": 0.0,
"learning_rate": 2.8600093817787778e-05,
"loss": 3.5014,
"step": 1307136
},
{
"epoch": 0.0,
"learning_rate": 2.8591707870277258e-05,
"loss": 3.5266,
"step": 1307648
},
{
"epoch": 0.0,
"learning_rate": 2.8583338301570467e-05,
"loss": 3.517,
"step": 1308160
},
{
"epoch": 0.0,
"learning_rate": 2.8574952354059947e-05,
"loss": 3.5134,
"step": 1308672
},
{
"epoch": 0.0,
"learning_rate": 2.8566566406549427e-05,
"loss": 3.5155,
"step": 1309184
},
{
"epoch": 0.0,
"learning_rate": 2.8558180459038907e-05,
"loss": 3.5316,
"step": 1309696
},
{
"epoch": 0.0,
"learning_rate": 2.854981089033212e-05,
"loss": 3.5021,
"step": 1310208
},
{
"epoch": 0.0,
"learning_rate": 2.85414249428216e-05,
"loss": 3.5089,
"step": 1310720
},
{
"epoch": 0.0,
"learning_rate": 2.853303899531108e-05,
"loss": 3.5194,
"step": 1311232
},
{
"epoch": 0.0,
"learning_rate": 2.852465304780056e-05,
"loss": 3.5089,
"step": 1311744
},
{
"epoch": 0.0,
"learning_rate": 2.8516283479093768e-05,
"loss": 3.4983,
"step": 1312256
},
{
"epoch": 0.01,
"learning_rate": 2.8507897531583248e-05,
"loss": 3.5036,
"step": 1312768
},
{
"epoch": 0.01,
"learning_rate": 2.849951158407273e-05,
"loss": 3.5177,
"step": 1313280
},
{
"epoch": 0.01,
"learning_rate": 2.849112563656221e-05,
"loss": 3.5158,
"step": 1313792
},
{
"epoch": 0.01,
"learning_rate": 2.848275606785542e-05,
"loss": 3.5146,
"step": 1314304
},
{
"epoch": 0.01,
"learning_rate": 2.84743701203449e-05,
"loss": 3.5123,
"step": 1314816
},
{
"epoch": 0.01,
"learning_rate": 2.846598417283438e-05,
"loss": 3.5151,
"step": 1315328
},
{
"epoch": 0.01,
"learning_rate": 2.845759822532386e-05,
"loss": 3.5145,
"step": 1315840
},
{
"epoch": 0.01,
"learning_rate": 2.8449228656617073e-05,
"loss": 3.5074,
"step": 1316352
},
{
"epoch": 0.01,
"learning_rate": 2.8440842709106553e-05,
"loss": 3.5114,
"step": 1316864
},
{
"epoch": 0.01,
"learning_rate": 2.8432456761596033e-05,
"loss": 3.498,
"step": 1317376
},
{
"epoch": 0.01,
"learning_rate": 2.8424070814085513e-05,
"loss": 3.5052,
"step": 1317888
},
{
"epoch": 0.01,
"learning_rate": 2.8415701245378722e-05,
"loss": 3.5069,
"step": 1318400
},
{
"epoch": 0.01,
"learning_rate": 2.8407315297868202e-05,
"loss": 3.5219,
"step": 1318912
},
{
"epoch": 0.01,
"learning_rate": 2.8398929350357685e-05,
"loss": 3.5079,
"step": 1319424
},
{
"epoch": 0.01,
"learning_rate": 2.8390543402847165e-05,
"loss": 3.5118,
"step": 1319936
},
{
"epoch": 0.01,
"learning_rate": 2.8382173834140374e-05,
"loss": 3.5125,
"step": 1320448
},
{
"epoch": 0.01,
"learning_rate": 2.8373787886629854e-05,
"loss": 3.5135,
"step": 1320960
},
{
"epoch": 0.01,
"learning_rate": 2.8365401939119334e-05,
"loss": 3.5178,
"step": 1321472
},
{
"epoch": 0.01,
"learning_rate": 2.8357015991608814e-05,
"loss": 3.487,
"step": 1321984
},
{
"epoch": 0.01,
"learning_rate": 2.8348646422902027e-05,
"loss": 3.507,
"step": 1322496
},
{
"epoch": 0.01,
"learning_rate": 2.8340260475391506e-05,
"loss": 3.5181,
"step": 1323008
},
{
"epoch": 0.01,
"learning_rate": 2.8331874527880986e-05,
"loss": 3.514,
"step": 1323520
},
{
"epoch": 0.01,
"learning_rate": 2.8323488580370466e-05,
"loss": 3.5055,
"step": 1324032
},
{
"epoch": 0.01,
"learning_rate": 2.8315119011663676e-05,
"loss": 3.5019,
"step": 1324544
},
{
"epoch": 0.01,
"learning_rate": 2.8306733064153155e-05,
"loss": 3.4997,
"step": 1325056
},
{
"epoch": 0.01,
"learning_rate": 2.829834711664264e-05,
"loss": 3.4909,
"step": 1325568
},
{
"epoch": 0.01,
"learning_rate": 2.8289961169132112e-05,
"loss": 3.5196,
"step": 1326080
},
{
"epoch": 0.01,
"learning_rate": 2.8281591600425328e-05,
"loss": 3.4983,
"step": 1326592
},
{
"epoch": 0.01,
"learning_rate": 2.8273205652914808e-05,
"loss": 3.5168,
"step": 1327104
},
{
"epoch": 0.01,
"learning_rate": 2.8264819705404288e-05,
"loss": 3.5082,
"step": 1327616
},
{
"epoch": 0.01,
"learning_rate": 2.8256433757893764e-05,
"loss": 3.4985,
"step": 1328128
},
{
"epoch": 0.01,
"learning_rate": 2.824806418918698e-05,
"loss": 3.5068,
"step": 1328640
},
{
"epoch": 0.01,
"learning_rate": 2.823967824167646e-05,
"loss": 3.4993,
"step": 1329152
},
{
"epoch": 0.01,
"learning_rate": 2.823129229416594e-05,
"loss": 3.5016,
"step": 1329664
},
{
"epoch": 0.01,
"learning_rate": 2.8222906346655413e-05,
"loss": 3.5016,
"step": 1330176
},
{
"epoch": 0.01,
"learning_rate": 2.821453677794863e-05,
"loss": 3.5194,
"step": 1330688
},
{
"epoch": 0.01,
"learning_rate": 2.820615083043811e-05,
"loss": 3.4917,
"step": 1331200
},
{
"epoch": 0.01,
"learning_rate": 2.8197764882927586e-05,
"loss": 3.4972,
"step": 1331712
},
{
"epoch": 0.01,
"learning_rate": 2.8189378935417066e-05,
"loss": 3.4889,
"step": 1332224
},
{
"epoch": 0.01,
"learning_rate": 2.818100936671028e-05,
"loss": 3.5,
"step": 1332736
},
{
"epoch": 0.01,
"learning_rate": 2.817262341919976e-05,
"loss": 3.5134,
"step": 1333248
},
{
"epoch": 0.01,
"learning_rate": 2.8164237471689238e-05,
"loss": 3.5086,
"step": 1333760
},
{
"epoch": 0.01,
"learning_rate": 2.8155851524178718e-05,
"loss": 3.5069,
"step": 1334272
},
{
"epoch": 0.01,
"learning_rate": 2.8147481955471934e-05,
"loss": 3.5142,
"step": 1334784
},
{
"epoch": 0.01,
"learning_rate": 2.8139096007961414e-05,
"loss": 3.5185,
"step": 1335296
},
{
"epoch": 0.01,
"learning_rate": 2.8130710060450887e-05,
"loss": 3.5049,
"step": 1335808
},
{
"epoch": 0.01,
"learning_rate": 2.8122324112940367e-05,
"loss": 3.5069,
"step": 1336320
},
{
"epoch": 0.01,
"learning_rate": 2.8113954544233583e-05,
"loss": 3.5036,
"step": 1336832
},
{
"epoch": 0.01,
"learning_rate": 2.810556859672306e-05,
"loss": 3.5027,
"step": 1337344
},
{
"epoch": 0.01,
"learning_rate": 2.809718264921254e-05,
"loss": 3.5076,
"step": 1337856
},
{
"epoch": 0.01,
"learning_rate": 2.808879670170202e-05,
"loss": 3.5004,
"step": 1338368
},
{
"epoch": 0.01,
"learning_rate": 2.8080427132995235e-05,
"loss": 3.5165,
"step": 1338880
},
{
"epoch": 0.01,
"learning_rate": 2.807204118548471e-05,
"loss": 3.5103,
"step": 1339392
},
{
"epoch": 0.01,
"learning_rate": 2.8063655237974192e-05,
"loss": 3.5059,
"step": 1339904
},
{
"epoch": 0.01,
"learning_rate": 2.8055285669267408e-05,
"loss": 3.4904,
"step": 1340416
},
{
"epoch": 0.01,
"learning_rate": 2.8046899721756888e-05,
"loss": 3.4966,
"step": 1340928
},
{
"epoch": 0.01,
"learning_rate": 2.803851377424636e-05,
"loss": 3.509,
"step": 1341440
},
{
"epoch": 0.01,
"learning_rate": 2.803012782673584e-05,
"loss": 3.5091,
"step": 1341952
},
{
"epoch": 0.01,
"learning_rate": 2.8021758258029057e-05,
"loss": 3.5073,
"step": 1342464
},
{
"epoch": 0.01,
"learning_rate": 2.8013372310518533e-05,
"loss": 3.5062,
"step": 1342976
},
{
"epoch": 0.02,
"learning_rate": 2.8004986363008013e-05,
"loss": 3.5105,
"step": 1343488
},
{
"epoch": 0.02,
"learning_rate": 2.7996600415497493e-05,
"loss": 3.4989,
"step": 1344000
},
{
"epoch": 0.02,
"learning_rate": 2.798823084679071e-05,
"loss": 3.4912,
"step": 1344512
},
{
"epoch": 0.02,
"learning_rate": 2.7979844899280182e-05,
"loss": 3.5129,
"step": 1345024
},
{
"epoch": 0.02,
"learning_rate": 2.7971458951769662e-05,
"loss": 3.5089,
"step": 1345536
},
{
"epoch": 0.02,
"learning_rate": 2.7963073004259145e-05,
"loss": 3.5112,
"step": 1346048
},
{
"epoch": 0.02,
"learning_rate": 2.795470343555236e-05,
"loss": 3.5037,
"step": 1346560
},
{
"epoch": 0.02,
"learning_rate": 2.7946317488041834e-05,
"loss": 3.5001,
"step": 1347072
},
{
"epoch": 0.02,
"learning_rate": 2.7937931540531314e-05,
"loss": 3.5117,
"step": 1347584
},
{
"epoch": 0.02,
"learning_rate": 2.7929545593020794e-05,
"loss": 3.5132,
"step": 1348096
},
{
"epoch": 0.02,
"learning_rate": 2.7921176024314007e-05,
"loss": 3.5058,
"step": 1348608
},
{
"epoch": 0.02,
"learning_rate": 2.7912790076803487e-05,
"loss": 3.5051,
"step": 1349120
},
{
"epoch": 0.02,
"learning_rate": 2.7904404129292967e-05,
"loss": 3.4945,
"step": 1349632
},
{
"epoch": 0.02,
"learning_rate": 2.7896018181782447e-05,
"loss": 3.5042,
"step": 1350144
},
{
"epoch": 0.02,
"learning_rate": 2.7887648613075656e-05,
"loss": 3.5097,
"step": 1350656
},
{
"epoch": 0.02,
"learning_rate": 2.7879262665565136e-05,
"loss": 3.4925,
"step": 1351168
},
{
"epoch": 0.02,
"learning_rate": 2.7870876718054616e-05,
"loss": 3.4987,
"step": 1351680
},
{
"epoch": 0.02,
"learning_rate": 2.78624907705441e-05,
"loss": 3.504,
"step": 1352192
},
{
"epoch": 0.02,
"learning_rate": 2.7854121201837308e-05,
"loss": 3.5107,
"step": 1352704
},
{
"epoch": 0.02,
"learning_rate": 2.7845735254326788e-05,
"loss": 3.4928,
"step": 1353216
},
{
"epoch": 0.02,
"learning_rate": 2.7837349306816268e-05,
"loss": 3.507,
"step": 1353728
},
{
"epoch": 0.02,
"learning_rate": 2.7828963359305748e-05,
"loss": 3.4971,
"step": 1354240
},
{
"epoch": 0.02,
"learning_rate": 2.782059379059896e-05,
"loss": 3.5135,
"step": 1354752
},
{
"epoch": 0.02,
"learning_rate": 2.781220784308844e-05,
"loss": 3.4969,
"step": 1355264
},
{
"epoch": 0.02,
"learning_rate": 2.780382189557792e-05,
"loss": 3.504,
"step": 1355776
},
{
"epoch": 0.02,
"learning_rate": 2.77954359480674e-05,
"loss": 3.5122,
"step": 1356288
},
{
"epoch": 0.02,
"learning_rate": 2.778706637936061e-05,
"loss": 3.5113,
"step": 1356800
},
{
"epoch": 0.02,
"learning_rate": 2.777868043185009e-05,
"loss": 3.5015,
"step": 1357312
},
{
"epoch": 0.02,
"learning_rate": 2.777029448433957e-05,
"loss": 3.4973,
"step": 1357824
},
{
"epoch": 0.02,
"learning_rate": 2.776190853682905e-05,
"loss": 3.5054,
"step": 1358336
},
{
"epoch": 0.02,
"learning_rate": 2.7753538968122262e-05,
"loss": 3.5063,
"step": 1358848
},
{
"epoch": 0.02,
"learning_rate": 2.7745153020611742e-05,
"loss": 3.4968,
"step": 1359360
},
{
"epoch": 0.02,
"learning_rate": 2.7736767073101222e-05,
"loss": 3.4991,
"step": 1359872
},
{
"epoch": 0.02,
"learning_rate": 2.77283811255907e-05,
"loss": 3.4978,
"step": 1360384
},
{
"epoch": 0.02,
"learning_rate": 2.7720011556883914e-05,
"loss": 3.5137,
"step": 1360896
},
{
"epoch": 0.02,
"learning_rate": 2.7711625609373394e-05,
"loss": 3.4945,
"step": 1361408
},
{
"epoch": 0.02,
"learning_rate": 2.7703239661862874e-05,
"loss": 3.5028,
"step": 1361920
},
{
"epoch": 0.02,
"learning_rate": 2.7694853714352354e-05,
"loss": 3.5,
"step": 1362432
},
{
"epoch": 0.02,
"learning_rate": 2.7686484145645563e-05,
"loss": 3.4992,
"step": 1362944
},
{
"epoch": 0.02,
"learning_rate": 2.7678098198135043e-05,
"loss": 3.4993,
"step": 1363456
},
{
"epoch": 0.02,
"learning_rate": 2.7669712250624523e-05,
"loss": 3.5169,
"step": 1363968
},
{
"epoch": 0.02,
"learning_rate": 2.7661326303114003e-05,
"loss": 3.5138,
"step": 1364480
},
{
"epoch": 0.02,
"learning_rate": 2.7652956734407215e-05,
"loss": 3.504,
"step": 1364992
},
{
"epoch": 0.02,
"learning_rate": 2.7644570786896695e-05,
"loss": 3.4953,
"step": 1365504
},
{
"epoch": 0.02,
"learning_rate": 2.7636184839386175e-05,
"loss": 3.5066,
"step": 1366016
},
{
"epoch": 0.02,
"learning_rate": 2.7627798891875655e-05,
"loss": 3.5067,
"step": 1366528
},
{
"epoch": 0.02,
"learning_rate": 2.7619429323168864e-05,
"loss": 3.5129,
"step": 1367040
},
{
"epoch": 0.02,
"learning_rate": 2.7611043375658348e-05,
"loss": 3.4898,
"step": 1367552
},
{
"epoch": 0.02,
"learning_rate": 2.7602657428147828e-05,
"loss": 3.5171,
"step": 1368064
},
{
"epoch": 0.02,
"learning_rate": 2.7594271480637308e-05,
"loss": 3.5057,
"step": 1368576
},
{
"epoch": 0.02,
"learning_rate": 2.7585901911930517e-05,
"loss": 3.5188,
"step": 1369088
},
{
"epoch": 0.02,
"learning_rate": 2.7577515964419997e-05,
"loss": 3.5024,
"step": 1369600
},
{
"epoch": 0.02,
"learning_rate": 2.7569130016909477e-05,
"loss": 3.5117,
"step": 1370112
},
{
"epoch": 0.02,
"learning_rate": 2.7560744069398957e-05,
"loss": 3.5077,
"step": 1370624
},
{
"epoch": 0.02,
"learning_rate": 2.755237450069217e-05,
"loss": 3.4926,
"step": 1371136
},
{
"epoch": 0.02,
"learning_rate": 2.754398855318165e-05,
"loss": 3.5151,
"step": 1371648
},
{
"epoch": 0.02,
"learning_rate": 2.753560260567113e-05,
"loss": 3.5099,
"step": 1372160
},
{
"epoch": 0.02,
"learning_rate": 2.752721665816061e-05,
"loss": 3.5078,
"step": 1372672
},
{
"epoch": 0.02,
"learning_rate": 2.7518847089453818e-05,
"loss": 3.5002,
"step": 1373184
},
{
"epoch": 0.02,
"learning_rate": 2.75104611419433e-05,
"loss": 3.5002,
"step": 1373696
},
{
"epoch": 0.03,
"eval_loss": 3.8494322299957275,
"eval_runtime": 305.2665,
"eval_samples_per_second": 1250.026,
"eval_steps_per_second": 39.064,
"step": 1373760
},
{
"epoch": 1.0,
"learning_rate": 2.750207519443278e-05,
"loss": 3.4925,
"step": 1374208
},
{
"epoch": 1.0,
"learning_rate": 2.749368924692226e-05,
"loss": 3.495,
"step": 1374720
},
{
"epoch": 1.0,
"learning_rate": 2.748531967821547e-05,
"loss": 3.5144,
"step": 1375232
},
{
"epoch": 1.0,
"learning_rate": 2.747693373070495e-05,
"loss": 3.5016,
"step": 1375744
},
{
"epoch": 1.0,
"learning_rate": 2.746854778319443e-05,
"loss": 3.5125,
"step": 1376256
},
{
"epoch": 1.0,
"learning_rate": 2.746016183568391e-05,
"loss": 3.4964,
"step": 1376768
},
{
"epoch": 1.0,
"learning_rate": 2.7451792266977123e-05,
"loss": 3.4972,
"step": 1377280
},
{
"epoch": 1.0,
"learning_rate": 2.7443406319466603e-05,
"loss": 3.492,
"step": 1377792
},
{
"epoch": 1.0,
"learning_rate": 2.7435020371956083e-05,
"loss": 3.5004,
"step": 1378304
},
{
"epoch": 1.0,
"learning_rate": 2.7426634424445563e-05,
"loss": 3.5045,
"step": 1378816
},
{
"epoch": 1.0,
"learning_rate": 2.7418264855738772e-05,
"loss": 3.5058,
"step": 1379328
},
{
"epoch": 1.0,
"learning_rate": 2.7409878908228255e-05,
"loss": 3.5104,
"step": 1379840
},
{
"epoch": 1.0,
"learning_rate": 2.7401509339521464e-05,
"loss": 3.5016,
"step": 1380352
},
{
"epoch": 1.0,
"learning_rate": 2.7393123392010944e-05,
"loss": 3.4905,
"step": 1380864
},
{
"epoch": 1.0,
"learning_rate": 2.7384737444500424e-05,
"loss": 3.494,
"step": 1381376
},
{
"epoch": 1.0,
"learning_rate": 2.7376351496989904e-05,
"loss": 3.4847,
"step": 1381888
},
{
"epoch": 1.0,
"learning_rate": 2.7367965549479384e-05,
"loss": 3.4961,
"step": 1382400
},
{
"epoch": 1.0,
"learning_rate": 2.7359579601968864e-05,
"loss": 3.4969,
"step": 1382912
},
{
"epoch": 1.0,
"learning_rate": 2.7351193654458347e-05,
"loss": 3.492,
"step": 1383424
},
{
"epoch": 1.0,
"learning_rate": 2.7342807706947827e-05,
"loss": 3.5169,
"step": 1383936
},
{
"epoch": 1.0,
"learning_rate": 2.7334438138241036e-05,
"loss": 3.5011,
"step": 1384448
},
{
"epoch": 1.0,
"learning_rate": 2.7326052190730516e-05,
"loss": 3.5028,
"step": 1384960
},
{
"epoch": 1.0,
"learning_rate": 2.7317666243219996e-05,
"loss": 3.5049,
"step": 1385472
},
{
"epoch": 1.0,
"learning_rate": 2.7309280295709476e-05,
"loss": 3.517,
"step": 1385984
},
{
"epoch": 1.0,
"learning_rate": 2.730091072700269e-05,
"loss": 3.4869,
"step": 1386496
},
{
"epoch": 1.0,
"learning_rate": 2.729252477949217e-05,
"loss": 3.4977,
"step": 1387008
},
{
"epoch": 1.0,
"learning_rate": 2.728413883198165e-05,
"loss": 3.5057,
"step": 1387520
},
{
"epoch": 1.0,
"learning_rate": 2.727575288447113e-05,
"loss": 3.4971,
"step": 1388032
},
{
"epoch": 1.0,
"learning_rate": 2.7267383315764338e-05,
"loss": 3.4916,
"step": 1388544
},
{
"epoch": 1.01,
"learning_rate": 2.7258997368253818e-05,
"loss": 3.4857,
"step": 1389056
},
{
"epoch": 1.01,
"learning_rate": 2.72506114207433e-05,
"loss": 3.507,
"step": 1389568
},
{
"epoch": 1.01,
"learning_rate": 2.724222547323278e-05,
"loss": 3.5037,
"step": 1390080
},
{
"epoch": 1.01,
"learning_rate": 2.723385590452599e-05,
"loss": 3.4965,
"step": 1390592
},
{
"epoch": 1.01,
"learning_rate": 2.722546995701547e-05,
"loss": 3.5036,
"step": 1391104
},
{
"epoch": 1.01,
"learning_rate": 2.721708400950495e-05,
"loss": 3.4999,
"step": 1391616
},
{
"epoch": 1.01,
"learning_rate": 2.720869806199443e-05,
"loss": 3.4985,
"step": 1392128
},
{
"epoch": 1.01,
"learning_rate": 2.7200328493287642e-05,
"loss": 3.4943,
"step": 1392640
},
{
"epoch": 1.01,
"learning_rate": 2.7191942545777122e-05,
"loss": 3.5034,
"step": 1393152
},
{
"epoch": 1.01,
"learning_rate": 2.7183556598266602e-05,
"loss": 3.4814,
"step": 1393664
},
{
"epoch": 1.01,
"learning_rate": 2.7175170650756082e-05,
"loss": 3.4924,
"step": 1394176
},
{
"epoch": 1.01,
"learning_rate": 2.716680108204929e-05,
"loss": 3.496,
"step": 1394688
},
{
"epoch": 1.01,
"learning_rate": 2.715841513453877e-05,
"loss": 3.5084,
"step": 1395200
},
{
"epoch": 1.01,
"learning_rate": 2.7150029187028255e-05,
"loss": 3.4968,
"step": 1395712
},
{
"epoch": 1.01,
"learning_rate": 2.7141643239517735e-05,
"loss": 3.4983,
"step": 1396224
},
{
"epoch": 1.01,
"learning_rate": 2.7133273670810944e-05,
"loss": 3.5035,
"step": 1396736
},
{
"epoch": 1.01,
"learning_rate": 2.7124887723300424e-05,
"loss": 3.499,
"step": 1397248
},
{
"epoch": 1.01,
"learning_rate": 2.7116501775789904e-05,
"loss": 3.5051,
"step": 1397760
},
{
"epoch": 1.01,
"learning_rate": 2.710811582827938e-05,
"loss": 3.4773,
"step": 1398272
},
{
"epoch": 1.01,
"learning_rate": 2.7099746259572596e-05,
"loss": 3.4996,
"step": 1398784
},
{
"epoch": 1.01,
"learning_rate": 2.7091360312062076e-05,
"loss": 3.5012,
"step": 1399296
},
{
"epoch": 1.01,
"learning_rate": 2.7082974364551556e-05,
"loss": 3.5037,
"step": 1399808
},
{
"epoch": 1.01,
"learning_rate": 2.707458841704103e-05,
"loss": 3.4918,
"step": 1400320
},
{
"epoch": 1.01,
"learning_rate": 2.7066218848334245e-05,
"loss": 3.4867,
"step": 1400832
},
{
"epoch": 1.01,
"learning_rate": 2.7057832900823725e-05,
"loss": 3.4915,
"step": 1401344
},
{
"epoch": 1.01,
"learning_rate": 2.704944695331321e-05,
"loss": 3.4753,
"step": 1401856
},
{
"epoch": 1.01,
"learning_rate": 2.704106100580268e-05,
"loss": 3.5082,
"step": 1402368
},
{
"epoch": 1.01,
"learning_rate": 2.7032691437095897e-05,
"loss": 3.4876,
"step": 1402880
},
{
"epoch": 1.01,
"learning_rate": 2.7024305489585377e-05,
"loss": 3.5008,
"step": 1403392
},
{
"epoch": 1.01,
"learning_rate": 2.7015919542074854e-05,
"loss": 3.4972,
"step": 1403904
},
{
"epoch": 1.01,
"learning_rate": 2.7007533594564334e-05,
"loss": 3.4863,
"step": 1404416
},
{
"epoch": 1.01,
"learning_rate": 2.699916402585755e-05,
"loss": 3.4935,
"step": 1404928
},
{
"epoch": 1.01,
"learning_rate": 2.699077807834703e-05,
"loss": 3.4856,
"step": 1405440
},
{
"epoch": 1.01,
"learning_rate": 2.6982392130836503e-05,
"loss": 3.4916,
"step": 1405952
},
{
"epoch": 1.01,
"learning_rate": 2.6974006183325983e-05,
"loss": 3.4834,
"step": 1406464
},
{
"epoch": 1.01,
"learning_rate": 2.69656366146192e-05,
"loss": 3.5043,
"step": 1406976
},
{
"epoch": 1.01,
"learning_rate": 2.695725066710868e-05,
"loss": 3.4847,
"step": 1407488
},
{
"epoch": 1.01,
"learning_rate": 2.6948864719598155e-05,
"loss": 3.486,
"step": 1408000
},
{
"epoch": 1.01,
"learning_rate": 2.694049515089137e-05,
"loss": 3.4768,
"step": 1408512
},
{
"epoch": 1.01,
"learning_rate": 2.693210920338085e-05,
"loss": 3.4882,
"step": 1409024
},
{
"epoch": 1.01,
"learning_rate": 2.6923723255870324e-05,
"loss": 3.4958,
"step": 1409536
},
{
"epoch": 1.01,
"learning_rate": 2.6915337308359808e-05,
"loss": 3.4991,
"step": 1410048
},
{
"epoch": 1.01,
"learning_rate": 2.6906951360849288e-05,
"loss": 3.494,
"step": 1410560
},
{
"epoch": 1.01,
"learning_rate": 2.6898581792142503e-05,
"loss": 3.5012,
"step": 1411072
},
{
"epoch": 1.01,
"learning_rate": 2.6890195844631977e-05,
"loss": 3.5065,
"step": 1411584
},
{
"epoch": 1.01,
"learning_rate": 2.6881809897121457e-05,
"loss": 3.4947,
"step": 1412096
},
{
"epoch": 1.01,
"learning_rate": 2.6873423949610937e-05,
"loss": 3.4864,
"step": 1412608
},
{
"epoch": 1.01,
"learning_rate": 2.6865054380904152e-05,
"loss": 3.4972,
"step": 1413120
},
{
"epoch": 1.01,
"learning_rate": 2.685666843339363e-05,
"loss": 3.4914,
"step": 1413632
},
{
"epoch": 1.01,
"learning_rate": 2.684828248588311e-05,
"loss": 3.4934,
"step": 1414144
},
{
"epoch": 1.01,
"learning_rate": 2.683989653837259e-05,
"loss": 3.4886,
"step": 1414656
},
{
"epoch": 1.01,
"learning_rate": 2.6831526969665798e-05,
"loss": 3.5007,
"step": 1415168
},
{
"epoch": 1.01,
"learning_rate": 2.6823141022155278e-05,
"loss": 3.5028,
"step": 1415680
},
{
"epoch": 1.01,
"learning_rate": 2.6814755074644758e-05,
"loss": 3.4902,
"step": 1416192
},
{
"epoch": 1.01,
"learning_rate": 2.680636912713424e-05,
"loss": 3.4791,
"step": 1416704
},
{
"epoch": 1.01,
"learning_rate": 2.679799955842745e-05,
"loss": 3.4838,
"step": 1417216
},
{
"epoch": 1.01,
"learning_rate": 2.678961361091693e-05,
"loss": 3.4931,
"step": 1417728
},
{
"epoch": 1.01,
"learning_rate": 2.678122766340641e-05,
"loss": 3.4978,
"step": 1418240
},
{
"epoch": 1.01,
"learning_rate": 2.677284171589589e-05,
"loss": 3.4938,
"step": 1418752
},
{
"epoch": 1.01,
"learning_rate": 2.6764472147189103e-05,
"loss": 3.4971,
"step": 1419264
},
{
"epoch": 1.02,
"learning_rate": 2.6756086199678583e-05,
"loss": 3.4965,
"step": 1419776
},
{
"epoch": 1.02,
"learning_rate": 2.6747700252168063e-05,
"loss": 3.4878,
"step": 1420288
},
{
"epoch": 1.02,
"learning_rate": 2.673933068346127e-05,
"loss": 3.4837,
"step": 1420800
},
{
"epoch": 1.02,
"learning_rate": 2.673094473595075e-05,
"loss": 3.4928,
"step": 1421312
},
{
"epoch": 1.02,
"learning_rate": 2.672255878844023e-05,
"loss": 3.4982,
"step": 1421824
},
{
"epoch": 1.02,
"learning_rate": 2.671417284092971e-05,
"loss": 3.4968,
"step": 1422336
},
{
"epoch": 1.02,
"learning_rate": 2.6705803272222924e-05,
"loss": 3.4942,
"step": 1422848
},
{
"epoch": 1.02,
"learning_rate": 2.6697417324712404e-05,
"loss": 3.4835,
"step": 1423360
},
{
"epoch": 1.02,
"learning_rate": 2.6689031377201884e-05,
"loss": 3.4987,
"step": 1423872
},
{
"epoch": 1.02,
"learning_rate": 2.6680645429691364e-05,
"loss": 3.5014,
"step": 1424384
},
{
"epoch": 1.02,
"learning_rate": 2.6672275860984573e-05,
"loss": 3.4924,
"step": 1424896
},
{
"epoch": 1.02,
"learning_rate": 2.6663889913474056e-05,
"loss": 3.4955,
"step": 1425408
},
{
"epoch": 1.02,
"learning_rate": 2.6655503965963536e-05,
"loss": 3.4816,
"step": 1425920
},
{
"epoch": 1.02,
"learning_rate": 2.6647118018453016e-05,
"loss": 3.4907,
"step": 1426432
},
{
"epoch": 1.02,
"learning_rate": 2.6638748449746225e-05,
"loss": 3.4982,
"step": 1426944
},
{
"epoch": 1.02,
"learning_rate": 2.6630362502235705e-05,
"loss": 3.4789,
"step": 1427456
},
{
"epoch": 1.02,
"learning_rate": 2.6621976554725185e-05,
"loss": 3.4886,
"step": 1427968
},
{
"epoch": 1.02,
"learning_rate": 2.6613590607214665e-05,
"loss": 3.4927,
"step": 1428480
},
{
"epoch": 1.02,
"learning_rate": 2.6605221038507878e-05,
"loss": 3.4946,
"step": 1428992
},
{
"epoch": 1.02,
"learning_rate": 2.6596835090997358e-05,
"loss": 3.4782,
"step": 1429504
},
{
"epoch": 1.02,
"learning_rate": 2.6588449143486838e-05,
"loss": 3.497,
"step": 1430016
},
{
"epoch": 1.02,
"learning_rate": 2.6580063195976318e-05,
"loss": 3.4838,
"step": 1430528
},
{
"epoch": 1.02,
"learning_rate": 2.6571677248465798e-05,
"loss": 3.4996,
"step": 1431040
},
{
"epoch": 1.02,
"learning_rate": 2.656330767975901e-05,
"loss": 3.487,
"step": 1431552
},
{
"epoch": 1.02,
"learning_rate": 2.655492173224849e-05,
"loss": 3.4873,
"step": 1432064
},
{
"epoch": 1.02,
"learning_rate": 2.654653578473797e-05,
"loss": 3.5,
"step": 1432576
},
{
"epoch": 1.02,
"learning_rate": 2.653814983722745e-05,
"loss": 3.5021,
"step": 1433088
},
{
"epoch": 1.02,
"learning_rate": 2.652978026852066e-05,
"loss": 3.4893,
"step": 1433600
},
{
"epoch": 1.02,
"learning_rate": 2.652139432101014e-05,
"loss": 3.4878,
"step": 1434112
},
{
"epoch": 1.02,
"learning_rate": 2.651300837349962e-05,
"loss": 3.4906,
"step": 1434624
},
{
"epoch": 1.02,
"learning_rate": 2.650463880479283e-05,
"loss": 3.4898,
"step": 1435136
},
{
"epoch": 1.02,
"learning_rate": 2.649625285728231e-05,
"loss": 3.4869,
"step": 1435648
},
{
"epoch": 1.02,
"learning_rate": 2.648786690977179e-05,
"loss": 3.4902,
"step": 1436160
},
{
"epoch": 1.02,
"learning_rate": 2.647948096226127e-05,
"loss": 3.4819,
"step": 1436672
},
{
"epoch": 1.02,
"learning_rate": 2.647109501475075e-05,
"loss": 3.4971,
"step": 1437184
},
{
"epoch": 1.02,
"learning_rate": 2.6462725446043964e-05,
"loss": 3.488,
"step": 1437696
},
{
"epoch": 1.02,
"learning_rate": 2.6454339498533444e-05,
"loss": 3.4893,
"step": 1438208
},
{
"epoch": 1.02,
"learning_rate": 2.6445953551022924e-05,
"loss": 3.4828,
"step": 1438720
},
{
"epoch": 1.02,
"learning_rate": 2.6437567603512404e-05,
"loss": 3.4897,
"step": 1439232
},
{
"epoch": 1.02,
"learning_rate": 2.6429198034805613e-05,
"loss": 3.4819,
"step": 1439744
},
{
"epoch": 1.02,
"learning_rate": 2.6420812087295093e-05,
"loss": 3.5045,
"step": 1440256
},
{
"epoch": 1.02,
"learning_rate": 2.6412426139784573e-05,
"loss": 3.5026,
"step": 1440768
},
{
"epoch": 1.02,
"learning_rate": 2.6404040192274056e-05,
"loss": 3.493,
"step": 1441280
},
{
"epoch": 1.02,
"learning_rate": 2.6395670623567265e-05,
"loss": 3.4811,
"step": 1441792
},
{
"epoch": 1.02,
"learning_rate": 2.6387284676056745e-05,
"loss": 3.4975,
"step": 1442304
},
{
"epoch": 1.02,
"learning_rate": 2.6378898728546225e-05,
"loss": 3.4954,
"step": 1442816
},
{
"epoch": 1.02,
"learning_rate": 2.6370529159839434e-05,
"loss": 3.497,
"step": 1443328
},
{
"epoch": 1.02,
"learning_rate": 2.6362143212328917e-05,
"loss": 3.4825,
"step": 1443840
},
{
"epoch": 1.02,
"learning_rate": 2.6353757264818397e-05,
"loss": 3.4971,
"step": 1444352
},
{
"epoch": 1.02,
"learning_rate": 2.6345371317307877e-05,
"loss": 3.498,
"step": 1444864
},
{
"epoch": 1.02,
"learning_rate": 2.6337001748601086e-05,
"loss": 3.5084,
"step": 1445376
},
{
"epoch": 1.02,
"learning_rate": 2.6328615801090566e-05,
"loss": 3.4939,
"step": 1445888
},
{
"epoch": 1.02,
"learning_rate": 2.6320229853580046e-05,
"loss": 3.4945,
"step": 1446400
},
{
"epoch": 1.02,
"learning_rate": 2.6311843906069526e-05,
"loss": 3.4971,
"step": 1446912
},
{
"epoch": 1.02,
"learning_rate": 2.630347433736274e-05,
"loss": 3.478,
"step": 1447424
},
{
"epoch": 1.02,
"learning_rate": 2.629508838985222e-05,
"loss": 3.5024,
"step": 1447936
},
{
"epoch": 1.02,
"learning_rate": 2.62867024423417e-05,
"loss": 3.5023,
"step": 1448448
},
{
"epoch": 1.02,
"learning_rate": 2.627831649483118e-05,
"loss": 3.4929,
"step": 1448960
},
{
"epoch": 1.02,
"learning_rate": 2.6269946926124388e-05,
"loss": 3.4906,
"step": 1449472
},
{
"epoch": 1.02,
"learning_rate": 2.626156097861387e-05,
"loss": 3.4838,
"step": 1449984
},
{
"epoch": 1.03,
"eval_loss": 3.8508119583129883,
"eval_runtime": 308.1159,
"eval_samples_per_second": 1238.466,
"eval_steps_per_second": 38.703,
"step": 1450080
},
{
"epoch": 0.0,
"learning_rate": 2.625317503110335e-05,
"loss": 3.4784,
"step": 1450496
},
{
"epoch": 0.0,
"learning_rate": 2.624478908359283e-05,
"loss": 3.4807,
"step": 1451008
},
{
"epoch": 0.0,
"learning_rate": 2.623640313608231e-05,
"loss": 3.5,
"step": 1451520
},
{
"epoch": 0.0,
"learning_rate": 2.622801718857179e-05,
"loss": 3.4884,
"step": 1452032
},
{
"epoch": 0.0,
"learning_rate": 2.6219647619865e-05,
"loss": 3.5044,
"step": 1452544
},
{
"epoch": 0.0,
"learning_rate": 2.621126167235448e-05,
"loss": 3.4827,
"step": 1453056
},
{
"epoch": 0.0,
"learning_rate": 2.6202875724843963e-05,
"loss": 3.4861,
"step": 1453568
},
{
"epoch": 0.0,
"learning_rate": 2.6194489777333443e-05,
"loss": 3.4766,
"step": 1454080
},
{
"epoch": 0.0,
"learning_rate": 2.6186120208626652e-05,
"loss": 3.4889,
"step": 1454592
},
{
"epoch": 0.0,
"learning_rate": 2.6177734261116132e-05,
"loss": 3.4909,
"step": 1455104
},
{
"epoch": 0.0,
"learning_rate": 2.6169348313605612e-05,
"loss": 3.496,
"step": 1455616
},
{
"epoch": 0.0,
"learning_rate": 2.6160962366095092e-05,
"loss": 3.4956,
"step": 1456128
},
{
"epoch": 0.0,
"learning_rate": 2.6152609176192034e-05,
"loss": 3.4895,
"step": 1456640
},
{
"epoch": 0.0,
"learning_rate": 2.6144223228681514e-05,
"loss": 3.4783,
"step": 1457152
},
{
"epoch": 0.0,
"learning_rate": 2.6135837281170994e-05,
"loss": 3.4827,
"step": 1457664
},
{
"epoch": 0.0,
"learning_rate": 2.6127451333660474e-05,
"loss": 3.4752,
"step": 1458176
},
{
"epoch": 0.0,
"learning_rate": 2.6119065386149954e-05,
"loss": 3.4814,
"step": 1458688
},
{
"epoch": 0.0,
"learning_rate": 2.6110679438639434e-05,
"loss": 3.4845,
"step": 1459200
},
{
"epoch": 0.0,
"learning_rate": 2.6102293491128917e-05,
"loss": 3.4788,
"step": 1459712
},
{
"epoch": 0.0,
"learning_rate": 2.6093907543618397e-05,
"loss": 3.5062,
"step": 1460224
},
{
"epoch": 0.0,
"learning_rate": 2.6085537974911606e-05,
"loss": 3.4892,
"step": 1460736
},
{
"epoch": 0.0,
"learning_rate": 2.6077152027401086e-05,
"loss": 3.4893,
"step": 1461248
},
{
"epoch": 0.0,
"learning_rate": 2.6068766079890566e-05,
"loss": 3.495,
"step": 1461760
},
{
"epoch": 0.0,
"learning_rate": 2.6060380132380046e-05,
"loss": 3.4986,
"step": 1462272
},
{
"epoch": 0.0,
"learning_rate": 2.6052010563673258e-05,
"loss": 3.4769,
"step": 1462784
},
{
"epoch": 0.0,
"learning_rate": 2.6043624616162738e-05,
"loss": 3.485,
"step": 1463296
},
{
"epoch": 0.0,
"learning_rate": 2.6035238668652218e-05,
"loss": 3.4934,
"step": 1463808
},
{
"epoch": 0.0,
"learning_rate": 2.6026852721141698e-05,
"loss": 3.4885,
"step": 1464320
},
{
"epoch": 0.0,
"learning_rate": 2.6018483152434907e-05,
"loss": 3.4746,
"step": 1464832
},
{
"epoch": 0.01,
"learning_rate": 2.6010097204924387e-05,
"loss": 3.4736,
"step": 1465344
},
{
"epoch": 0.01,
"learning_rate": 2.6001711257413867e-05,
"loss": 3.4951,
"step": 1465856
},
{
"epoch": 0.01,
"learning_rate": 2.599332530990335e-05,
"loss": 3.4915,
"step": 1466368
},
{
"epoch": 0.01,
"learning_rate": 2.598495574119656e-05,
"loss": 3.4875,
"step": 1466880
},
{
"epoch": 0.01,
"learning_rate": 2.597656979368604e-05,
"loss": 3.4898,
"step": 1467392
},
{
"epoch": 0.01,
"learning_rate": 2.596818384617552e-05,
"loss": 3.4857,
"step": 1467904
},
{
"epoch": 0.01,
"learning_rate": 2.5959797898665e-05,
"loss": 3.4869,
"step": 1468416
},
{
"epoch": 0.01,
"learning_rate": 2.5951428329958212e-05,
"loss": 3.4794,
"step": 1468928
},
{
"epoch": 0.01,
"learning_rate": 2.5943042382447692e-05,
"loss": 3.4948,
"step": 1469440
},
{
"epoch": 0.01,
"learning_rate": 2.5934656434937172e-05,
"loss": 3.4728,
"step": 1469952
},
{
"epoch": 0.01,
"learning_rate": 2.5926270487426652e-05,
"loss": 3.479,
"step": 1470464
},
{
"epoch": 0.01,
"learning_rate": 2.591790091871986e-05,
"loss": 3.4794,
"step": 1470976
},
{
"epoch": 0.01,
"learning_rate": 2.590951497120934e-05,
"loss": 3.4975,
"step": 1471488
},
{
"epoch": 0.01,
"learning_rate": 2.590112902369882e-05,
"loss": 3.4871,
"step": 1472000
},
{
"epoch": 0.01,
"learning_rate": 2.5892743076188297e-05,
"loss": 3.4839,
"step": 1472512
},
{
"epoch": 0.01,
"learning_rate": 2.5884373507481513e-05,
"loss": 3.4898,
"step": 1473024
},
{
"epoch": 0.01,
"learning_rate": 2.5875987559970993e-05,
"loss": 3.4894,
"step": 1473536
},
{
"epoch": 0.01,
"learning_rate": 2.5867601612460473e-05,
"loss": 3.4905,
"step": 1474048
},
{
"epoch": 0.01,
"learning_rate": 2.585921566494995e-05,
"loss": 3.4678,
"step": 1474560
},
{
"epoch": 0.01,
"learning_rate": 2.5850846096243166e-05,
"loss": 3.4814,
"step": 1475072
},
{
"epoch": 0.01,
"learning_rate": 2.5842460148732646e-05,
"loss": 3.49,
"step": 1475584
},
{
"epoch": 0.01,
"learning_rate": 2.583407420122212e-05,
"loss": 3.4895,
"step": 1476096
},
{
"epoch": 0.01,
"learning_rate": 2.58256882537116e-05,
"loss": 3.4801,
"step": 1476608
},
{
"epoch": 0.01,
"learning_rate": 2.5817318685004815e-05,
"loss": 3.4771,
"step": 1477120
},
{
"epoch": 0.01,
"learning_rate": 2.5808932737494295e-05,
"loss": 3.48,
"step": 1477632
},
{
"epoch": 0.01,
"learning_rate": 2.580054678998377e-05,
"loss": 3.466,
"step": 1478144
},
{
"epoch": 0.01,
"learning_rate": 2.579216084247325e-05,
"loss": 3.4918,
"step": 1478656
},
{
"epoch": 0.01,
"learning_rate": 2.5783791273766467e-05,
"loss": 3.4753,
"step": 1479168
},
{
"epoch": 0.01,
"learning_rate": 2.5775405326255947e-05,
"loss": 3.4907,
"step": 1479680
},
{
"epoch": 0.01,
"learning_rate": 2.576701937874542e-05,
"loss": 3.4866,
"step": 1480192
},
{
"epoch": 0.01,
"learning_rate": 2.5758633431234903e-05,
"loss": 3.4735,
"step": 1480704
},
{
"epoch": 0.01,
"learning_rate": 2.575026386252812e-05,
"loss": 3.4785,
"step": 1481216
},
{
"epoch": 0.01,
"learning_rate": 2.5741877915017592e-05,
"loss": 3.4756,
"step": 1481728
},
{
"epoch": 0.01,
"learning_rate": 2.5733491967507072e-05,
"loss": 3.4768,
"step": 1482240
},
{
"epoch": 0.01,
"learning_rate": 2.5725122398800288e-05,
"loss": 3.4782,
"step": 1482752
},
{
"epoch": 0.01,
"learning_rate": 2.5716736451289768e-05,
"loss": 3.4873,
"step": 1483264
},
{
"epoch": 0.01,
"learning_rate": 2.5708350503779245e-05,
"loss": 3.4751,
"step": 1483776
},
{
"epoch": 0.01,
"learning_rate": 2.5699964556268725e-05,
"loss": 3.4747,
"step": 1484288
},
{
"epoch": 0.01,
"learning_rate": 2.569159498756194e-05,
"loss": 3.4656,
"step": 1484800
},
{
"epoch": 0.01,
"learning_rate": 2.568320904005142e-05,
"loss": 3.4742,
"step": 1485312
},
{
"epoch": 0.01,
"learning_rate": 2.5674823092540894e-05,
"loss": 3.4816,
"step": 1485824
},
{
"epoch": 0.01,
"learning_rate": 2.5666437145030374e-05,
"loss": 3.4932,
"step": 1486336
},
{
"epoch": 0.01,
"learning_rate": 2.565806757632359e-05,
"loss": 3.4783,
"step": 1486848
},
{
"epoch": 0.01,
"learning_rate": 2.5649681628813066e-05,
"loss": 3.4875,
"step": 1487360
},
{
"epoch": 0.01,
"learning_rate": 2.5641295681302546e-05,
"loss": 3.4917,
"step": 1487872
},
{
"epoch": 0.01,
"learning_rate": 2.5632909733792026e-05,
"loss": 3.4901,
"step": 1488384
},
{
"epoch": 0.01,
"learning_rate": 2.5624540165085242e-05,
"loss": 3.4686,
"step": 1488896
},
{
"epoch": 0.01,
"learning_rate": 2.561615421757472e-05,
"loss": 3.4872,
"step": 1489408
},
{
"epoch": 0.01,
"learning_rate": 2.56077682700642e-05,
"loss": 3.4805,
"step": 1489920
},
{
"epoch": 0.01,
"learning_rate": 2.559938232255368e-05,
"loss": 3.4756,
"step": 1490432
},
{
"epoch": 0.01,
"learning_rate": 2.5591012753846894e-05,
"loss": 3.4828,
"step": 1490944
},
{
"epoch": 0.01,
"learning_rate": 2.5582626806336367e-05,
"loss": 3.4842,
"step": 1491456
},
{
"epoch": 0.01,
"learning_rate": 2.5574240858825847e-05,
"loss": 3.4918,
"step": 1491968
},
{
"epoch": 0.01,
"learning_rate": 2.5565854911315327e-05,
"loss": 3.479,
"step": 1492480
},
{
"epoch": 0.01,
"learning_rate": 2.555748534260854e-05,
"loss": 3.4657,
"step": 1492992
},
{
"epoch": 0.01,
"learning_rate": 2.554909939509802e-05,
"loss": 3.474,
"step": 1493504
},
{
"epoch": 0.01,
"learning_rate": 2.55407134475875e-05,
"loss": 3.4778,
"step": 1494016
},
{
"epoch": 0.01,
"learning_rate": 2.553232750007698e-05,
"loss": 3.4852,
"step": 1494528
},
{
"epoch": 0.01,
"learning_rate": 2.552395793137019e-05,
"loss": 3.4848,
"step": 1495040
},
{
"epoch": 0.01,
"learning_rate": 2.5515571983859672e-05,
"loss": 3.482,
"step": 1495552
},
{
"epoch": 0.02,
"learning_rate": 2.5507186036349152e-05,
"loss": 3.4845,
"step": 1496064
},
{
"epoch": 0.02,
"learning_rate": 2.5498800088838632e-05,
"loss": 3.4722,
"step": 1496576
},
{
"epoch": 0.02,
"learning_rate": 2.549043052013184e-05,
"loss": 3.4708,
"step": 1497088
},
{
"epoch": 0.02,
"learning_rate": 2.548204457262132e-05,
"loss": 3.4794,
"step": 1497600
},
{
"epoch": 0.02,
"learning_rate": 2.54736586251108e-05,
"loss": 3.4874,
"step": 1498112
},
{
"epoch": 0.02,
"learning_rate": 2.546527267760028e-05,
"loss": 3.4826,
"step": 1498624
},
{
"epoch": 0.02,
"learning_rate": 2.5456903108893494e-05,
"loss": 3.4911,
"step": 1499136
},
{
"epoch": 0.02,
"learning_rate": 2.5448517161382974e-05,
"loss": 3.4666,
"step": 1499648
},
{
"epoch": 0.02,
"learning_rate": 2.5440131213872453e-05,
"loss": 3.4894,
"step": 1500160
},
{
"epoch": 0.02,
"learning_rate": 2.5431745266361933e-05,
"loss": 3.488,
"step": 1500672
},
{
"epoch": 0.02,
"learning_rate": 2.5423375697655143e-05,
"loss": 3.4813,
"step": 1501184
},
{
"epoch": 0.02,
"learning_rate": 2.5414989750144626e-05,
"loss": 3.4821,
"step": 1501696
},
{
"epoch": 0.02,
"learning_rate": 2.5406603802634106e-05,
"loss": 3.4704,
"step": 1502208
},
{
"epoch": 0.02,
"learning_rate": 2.5398217855123586e-05,
"loss": 3.479,
"step": 1502720
},
{
"epoch": 0.02,
"learning_rate": 2.5389848286416795e-05,
"loss": 3.4839,
"step": 1503232
},
{
"epoch": 0.02,
"learning_rate": 2.5381462338906275e-05,
"loss": 3.4672,
"step": 1503744
},
{
"epoch": 0.02,
"learning_rate": 2.5373076391395755e-05,
"loss": 3.4774,
"step": 1504256
},
{
"epoch": 0.02,
"learning_rate": 2.5364690443885235e-05,
"loss": 3.4782,
"step": 1504768
},
{
"epoch": 0.02,
"learning_rate": 2.5356320875178447e-05,
"loss": 3.4829,
"step": 1505280
},
{
"epoch": 0.02,
"learning_rate": 2.5347934927667927e-05,
"loss": 3.4649,
"step": 1505792
},
{
"epoch": 0.02,
"learning_rate": 2.5339548980157407e-05,
"loss": 3.4888,
"step": 1506304
},
{
"epoch": 0.02,
"learning_rate": 2.5331163032646887e-05,
"loss": 3.4647,
"step": 1506816
},
{
"epoch": 0.02,
"learning_rate": 2.5322793463940096e-05,
"loss": 3.4887,
"step": 1507328
},
{
"epoch": 0.02,
"learning_rate": 2.531440751642958e-05,
"loss": 3.477,
"step": 1507840
},
{
"epoch": 0.02,
"learning_rate": 2.530602156891906e-05,
"loss": 3.4736,
"step": 1508352
},
{
"epoch": 0.02,
"learning_rate": 2.529763562140854e-05,
"loss": 3.4881,
"step": 1508864
},
{
"epoch": 0.02,
"learning_rate": 2.528926605270175e-05,
"loss": 3.491,
"step": 1509376
},
{
"epoch": 0.02,
"learning_rate": 2.528088010519123e-05,
"loss": 3.4775,
"step": 1509888
},
{
"epoch": 0.02,
"learning_rate": 2.527249415768071e-05,
"loss": 3.4759,
"step": 1510400
},
{
"epoch": 0.02,
"learning_rate": 2.526410821017019e-05,
"loss": 3.4793,
"step": 1510912
},
{
"epoch": 0.02,
"learning_rate": 2.52557386414634e-05,
"loss": 3.4785,
"step": 1511424
},
{
"epoch": 0.02,
"learning_rate": 2.524735269395288e-05,
"loss": 3.4711,
"step": 1511936
},
{
"epoch": 0.02,
"learning_rate": 2.523896674644236e-05,
"loss": 3.4761,
"step": 1512448
},
{
"epoch": 0.02,
"learning_rate": 2.523058079893184e-05,
"loss": 3.4756,
"step": 1512960
},
{
"epoch": 0.02,
"learning_rate": 2.522221123022505e-05,
"loss": 3.4804,
"step": 1513472
},
{
"epoch": 0.02,
"learning_rate": 2.5213825282714533e-05,
"loss": 3.4794,
"step": 1513984
},
{
"epoch": 0.02,
"learning_rate": 2.5205439335204013e-05,
"loss": 3.4799,
"step": 1514496
},
{
"epoch": 0.02,
"learning_rate": 2.5197053387693493e-05,
"loss": 3.4642,
"step": 1515008
},
{
"epoch": 0.02,
"learning_rate": 2.5188683818986702e-05,
"loss": 3.4765,
"step": 1515520
},
{
"epoch": 0.02,
"learning_rate": 2.5180297871476182e-05,
"loss": 3.4758,
"step": 1516032
},
{
"epoch": 0.02,
"learning_rate": 2.5171911923965662e-05,
"loss": 3.4884,
"step": 1516544
},
{
"epoch": 0.02,
"learning_rate": 2.5163525976455142e-05,
"loss": 3.4884,
"step": 1517056
},
{
"epoch": 0.02,
"learning_rate": 2.5155156407748355e-05,
"loss": 3.4841,
"step": 1517568
},
{
"epoch": 0.02,
"learning_rate": 2.5146770460237835e-05,
"loss": 3.4667,
"step": 1518080
},
{
"epoch": 0.02,
"learning_rate": 2.5138384512727314e-05,
"loss": 3.4835,
"step": 1518592
},
{
"epoch": 0.02,
"learning_rate": 2.5129998565216794e-05,
"loss": 3.4817,
"step": 1519104
},
{
"epoch": 0.02,
"learning_rate": 2.5121628996510004e-05,
"loss": 3.4861,
"step": 1519616
},
{
"epoch": 0.02,
"learning_rate": 2.5113243048999487e-05,
"loss": 3.4686,
"step": 1520128
},
{
"epoch": 0.02,
"learning_rate": 2.5104857101488967e-05,
"loss": 3.4865,
"step": 1520640
},
{
"epoch": 0.02,
"learning_rate": 2.5096471153978447e-05,
"loss": 3.4878,
"step": 1521152
},
{
"epoch": 0.02,
"learning_rate": 2.5088101585271656e-05,
"loss": 3.4972,
"step": 1521664
},
{
"epoch": 0.02,
"learning_rate": 2.5079715637761136e-05,
"loss": 3.4755,
"step": 1522176
},
{
"epoch": 0.02,
"learning_rate": 2.5071329690250616e-05,
"loss": 3.4825,
"step": 1522688
},
{
"epoch": 0.02,
"learning_rate": 2.5062943742740096e-05,
"loss": 3.4841,
"step": 1523200
},
{
"epoch": 0.02,
"learning_rate": 2.5054574174033308e-05,
"loss": 3.4727,
"step": 1523712
},
{
"epoch": 0.02,
"learning_rate": 2.5046188226522788e-05,
"loss": 3.4835,
"step": 1524224
},
{
"epoch": 0.02,
"learning_rate": 2.5037802279012268e-05,
"loss": 3.491,
"step": 1524736
},
{
"epoch": 0.02,
"learning_rate": 2.5029416331501748e-05,
"loss": 3.4807,
"step": 1525248
},
{
"epoch": 0.02,
"learning_rate": 2.5021046762794957e-05,
"loss": 3.4761,
"step": 1525760
},
{
"epoch": 0.02,
"learning_rate": 2.5012660815284437e-05,
"loss": 3.4768,
"step": 1526272
},
{
"epoch": 0.03,
"eval_loss": 3.852536916732788,
"eval_runtime": 314.7327,
"eval_samples_per_second": 1212.429,
"eval_steps_per_second": 37.889,
"step": 1526400
},
{
"epoch": 0.0,
"learning_rate": 2.500427486777392e-05,
"loss": 3.4658,
"step": 1526784
},
{
"epoch": 0.0,
"learning_rate": 2.49958889202634e-05,
"loss": 3.4708,
"step": 1527296
},
{
"epoch": 0.0,
"learning_rate": 2.498750297275288e-05,
"loss": 3.4827,
"step": 1527808
},
{
"epoch": 0.0,
"learning_rate": 2.4979117025242357e-05,
"loss": 3.4797,
"step": 1528320
},
{
"epoch": 0.0,
"learning_rate": 2.497074745653557e-05,
"loss": 3.4907,
"step": 1528832
},
{
"epoch": 0.0,
"learning_rate": 2.496236150902505e-05,
"loss": 3.4735,
"step": 1529344
},
{
"epoch": 0.0,
"learning_rate": 2.495397556151453e-05,
"loss": 3.475,
"step": 1529856
},
{
"epoch": 0.0,
"learning_rate": 2.494558961400401e-05,
"loss": 3.4619,
"step": 1530368
},
{
"epoch": 0.0,
"learning_rate": 2.4937220045297222e-05,
"loss": 3.4794,
"step": 1530880
},
{
"epoch": 0.0,
"learning_rate": 2.4928834097786702e-05,
"loss": 3.4777,
"step": 1531392
},
{
"epoch": 0.0,
"learning_rate": 2.492044815027618e-05,
"loss": 3.4788,
"step": 1531904
},
{
"epoch": 0.0,
"learning_rate": 2.4912062202765658e-05,
"loss": 3.4869,
"step": 1532416
},
{
"epoch": 0.0,
"learning_rate": 2.4903709012862603e-05,
"loss": 3.4748,
"step": 1532928
},
{
"epoch": 0.0,
"learning_rate": 2.4895323065352083e-05,
"loss": 3.4707,
"step": 1533440
},
{
"epoch": 0.0,
"learning_rate": 2.4886937117841563e-05,
"loss": 3.4695,
"step": 1533952
},
{
"epoch": 0.0,
"learning_rate": 2.4878551170331043e-05,
"loss": 3.4645,
"step": 1534464
},
{
"epoch": 0.0,
"learning_rate": 2.4870165222820523e-05,
"loss": 3.4719,
"step": 1534976
},
{
"epoch": 0.0,
"learning_rate": 2.4861779275310003e-05,
"loss": 3.4735,
"step": 1535488
},
{
"epoch": 0.0,
"learning_rate": 2.4853393327799483e-05,
"loss": 3.469,
"step": 1536000
},
{
"epoch": 0.0,
"learning_rate": 2.4845007380288963e-05,
"loss": 3.4898,
"step": 1536512
},
{
"epoch": 0.0,
"learning_rate": 2.4836637811582175e-05,
"loss": 3.4768,
"step": 1537024
},
{
"epoch": 0.0,
"learning_rate": 2.4828251864071652e-05,
"loss": 3.4743,
"step": 1537536
},
{
"epoch": 0.0,
"learning_rate": 2.4819865916561132e-05,
"loss": 3.4846,
"step": 1538048
},
{
"epoch": 0.0,
"learning_rate": 2.4811496347854344e-05,
"loss": 3.4868,
"step": 1538560
},
{
"epoch": 0.0,
"learning_rate": 2.4803110400343828e-05,
"loss": 3.4705,
"step": 1539072
},
{
"epoch": 0.0,
"learning_rate": 2.4794724452833304e-05,
"loss": 3.4765,
"step": 1539584
},
{
"epoch": 0.0,
"learning_rate": 2.4786338505322784e-05,
"loss": 3.4784,
"step": 1540096
},
{
"epoch": 0.0,
"learning_rate": 2.4777968936615997e-05,
"loss": 3.4741,
"step": 1540608
},
{
"epoch": 0.0,
"learning_rate": 2.4769582989105473e-05,
"loss": 3.4614,
"step": 1541120
},
{
"epoch": 0.0,
"learning_rate": 2.4761197041594957e-05,
"loss": 3.4635,
"step": 1541632
},
{
"epoch": 0.01,
"learning_rate": 2.4752811094084437e-05,
"loss": 3.4836,
"step": 1542144
},
{
"epoch": 0.01,
"learning_rate": 2.474444152537765e-05,
"loss": 3.4825,
"step": 1542656
},
{
"epoch": 0.01,
"learning_rate": 2.4736055577867126e-05,
"loss": 3.4754,
"step": 1543168
},
{
"epoch": 0.01,
"learning_rate": 2.4727669630356606e-05,
"loss": 3.4809,
"step": 1543680
},
{
"epoch": 0.01,
"learning_rate": 2.4719283682846086e-05,
"loss": 3.4703,
"step": 1544192
},
{
"epoch": 0.01,
"learning_rate": 2.4710914114139298e-05,
"loss": 3.4784,
"step": 1544704
},
{
"epoch": 0.01,
"learning_rate": 2.4702528166628778e-05,
"loss": 3.4708,
"step": 1545216
},
{
"epoch": 0.01,
"learning_rate": 2.4694142219118258e-05,
"loss": 3.4772,
"step": 1545728
},
{
"epoch": 0.01,
"learning_rate": 2.4685756271607738e-05,
"loss": 3.4617,
"step": 1546240
},
{
"epoch": 0.01,
"learning_rate": 2.4677386702900947e-05,
"loss": 3.4676,
"step": 1546752
},
{
"epoch": 0.01,
"learning_rate": 2.4669000755390427e-05,
"loss": 3.4646,
"step": 1547264
},
{
"epoch": 0.01,
"learning_rate": 2.466061480787991e-05,
"loss": 3.4886,
"step": 1547776
},
{
"epoch": 0.01,
"learning_rate": 2.465222886036939e-05,
"loss": 3.4744,
"step": 1548288
},
{
"epoch": 0.01,
"learning_rate": 2.46438592916626e-05,
"loss": 3.4726,
"step": 1548800
},
{
"epoch": 0.01,
"learning_rate": 2.463547334415208e-05,
"loss": 3.4785,
"step": 1549312
},
{
"epoch": 0.01,
"learning_rate": 2.462708739664156e-05,
"loss": 3.4777,
"step": 1549824
},
{
"epoch": 0.01,
"learning_rate": 2.461870144913104e-05,
"loss": 3.4798,
"step": 1550336
},
{
"epoch": 0.01,
"learning_rate": 2.4610331880424252e-05,
"loss": 3.4589,
"step": 1550848
},
{
"epoch": 0.01,
"learning_rate": 2.4601945932913732e-05,
"loss": 3.468,
"step": 1551360
},
{
"epoch": 0.01,
"learning_rate": 2.4593559985403212e-05,
"loss": 3.4808,
"step": 1551872
},
{
"epoch": 0.01,
"learning_rate": 2.458517403789269e-05,
"loss": 3.4793,
"step": 1552384
},
{
"epoch": 0.01,
"learning_rate": 2.45768044691859e-05,
"loss": 3.465,
"step": 1552896
},
{
"epoch": 0.01,
"learning_rate": 2.456841852167538e-05,
"loss": 3.4648,
"step": 1553408
},
{
"epoch": 0.01,
"learning_rate": 2.456003257416486e-05,
"loss": 3.4683,
"step": 1553920
},
{
"epoch": 0.01,
"learning_rate": 2.4551646626654344e-05,
"loss": 3.4567,
"step": 1554432
},
{
"epoch": 0.01,
"learning_rate": 2.4543277057947553e-05,
"loss": 3.4751,
"step": 1554944
},
{
"epoch": 0.01,
"learning_rate": 2.4534891110437033e-05,
"loss": 3.4638,
"step": 1555456
},
{
"epoch": 0.01,
"learning_rate": 2.4526505162926513e-05,
"loss": 3.4768,
"step": 1555968
},
{
"epoch": 0.01,
"learning_rate": 2.4518119215415993e-05,
"loss": 3.4736,
"step": 1556480
},
{
"epoch": 0.01,
"learning_rate": 2.4509749646709205e-05,
"loss": 3.4687,
"step": 1556992
},
{
"epoch": 0.01,
"learning_rate": 2.4501363699198685e-05,
"loss": 3.463,
"step": 1557504
},
{
"epoch": 0.01,
"learning_rate": 2.4492977751688165e-05,
"loss": 3.467,
"step": 1558016
},
{
"epoch": 0.01,
"learning_rate": 2.4484591804177645e-05,
"loss": 3.4621,
"step": 1558528
},
{
"epoch": 0.01,
"learning_rate": 2.4476222235470854e-05,
"loss": 3.4686,
"step": 1559040
},
{
"epoch": 0.01,
"learning_rate": 2.4467836287960334e-05,
"loss": 3.4739,
"step": 1559552
},
{
"epoch": 0.01,
"learning_rate": 2.4459450340449814e-05,
"loss": 3.4634,
"step": 1560064
},
{
"epoch": 0.01,
"learning_rate": 2.4451064392939298e-05,
"loss": 3.4636,
"step": 1560576
},
{
"epoch": 0.01,
"learning_rate": 2.4442694824232507e-05,
"loss": 3.454,
"step": 1561088
},
{
"epoch": 0.01,
"learning_rate": 2.4434308876721987e-05,
"loss": 3.4602,
"step": 1561600
},
{
"epoch": 0.01,
"learning_rate": 2.4425922929211467e-05,
"loss": 3.4699,
"step": 1562112
},
{
"epoch": 0.01,
"learning_rate": 2.4417536981700947e-05,
"loss": 3.4785,
"step": 1562624
},
{
"epoch": 0.01,
"learning_rate": 2.440916741299416e-05,
"loss": 3.4675,
"step": 1563136
},
{
"epoch": 0.01,
"learning_rate": 2.440078146548364e-05,
"loss": 3.4772,
"step": 1563648
},
{
"epoch": 0.01,
"learning_rate": 2.439239551797312e-05,
"loss": 3.4816,
"step": 1564160
},
{
"epoch": 0.01,
"learning_rate": 2.43840095704626e-05,
"loss": 3.4761,
"step": 1564672
},
{
"epoch": 0.01,
"learning_rate": 2.4375640001755808e-05,
"loss": 3.4572,
"step": 1565184
},
{
"epoch": 0.01,
"learning_rate": 2.4367254054245288e-05,
"loss": 3.4729,
"step": 1565696
},
{
"epoch": 0.01,
"learning_rate": 2.4358868106734768e-05,
"loss": 3.4694,
"step": 1566208
},
{
"epoch": 0.01,
"learning_rate": 2.435048215922425e-05,
"loss": 3.4625,
"step": 1566720
},
{
"epoch": 0.01,
"learning_rate": 2.434211259051746e-05,
"loss": 3.4704,
"step": 1567232
},
{
"epoch": 0.01,
"learning_rate": 2.433372664300694e-05,
"loss": 3.4749,
"step": 1567744
},
{
"epoch": 0.01,
"learning_rate": 2.432534069549642e-05,
"loss": 3.4818,
"step": 1568256
},
{
"epoch": 0.01,
"learning_rate": 2.4316954747985897e-05,
"loss": 3.4663,
"step": 1568768
},
{
"epoch": 0.01,
"learning_rate": 2.4308585179279113e-05,
"loss": 3.4526,
"step": 1569280
},
{
"epoch": 0.01,
"learning_rate": 2.4300199231768593e-05,
"loss": 3.4661,
"step": 1569792
},
{
"epoch": 0.01,
"learning_rate": 2.4291813284258073e-05,
"loss": 3.4661,
"step": 1570304
},
{
"epoch": 0.01,
"learning_rate": 2.428342733674755e-05,
"loss": 3.4706,
"step": 1570816
},
{
"epoch": 0.01,
"learning_rate": 2.4275057768040762e-05,
"loss": 3.472,
"step": 1571328
},
{
"epoch": 0.01,
"learning_rate": 2.4266671820530242e-05,
"loss": 3.4722,
"step": 1571840
},
{
"epoch": 0.02,
"learning_rate": 2.425828587301972e-05,
"loss": 3.4735,
"step": 1572352
},
{
"epoch": 0.02,
"learning_rate": 2.42498999255092e-05,
"loss": 3.4618,
"step": 1572864
},
{
"epoch": 0.02,
"learning_rate": 2.4241530356802414e-05,
"loss": 3.4588,
"step": 1573376
},
{
"epoch": 0.02,
"learning_rate": 2.4233144409291894e-05,
"loss": 3.4653,
"step": 1573888
},
{
"epoch": 0.02,
"learning_rate": 2.422475846178137e-05,
"loss": 3.4781,
"step": 1574400
},
{
"epoch": 0.02,
"learning_rate": 2.421637251427085e-05,
"loss": 3.4708,
"step": 1574912
},
{
"epoch": 0.02,
"learning_rate": 2.4208002945564066e-05,
"loss": 3.4792,
"step": 1575424
},
{
"epoch": 0.02,
"learning_rate": 2.4199616998053546e-05,
"loss": 3.4556,
"step": 1575936
},
{
"epoch": 0.02,
"learning_rate": 2.4191231050543023e-05,
"loss": 3.4737,
"step": 1576448
},
{
"epoch": 0.02,
"learning_rate": 2.4182845103032503e-05,
"loss": 3.475,
"step": 1576960
},
{
"epoch": 0.02,
"learning_rate": 2.4174475534325715e-05,
"loss": 3.473,
"step": 1577472
},
{
"epoch": 0.02,
"learning_rate": 2.4166089586815195e-05,
"loss": 3.468,
"step": 1577984
},
{
"epoch": 0.02,
"learning_rate": 2.4157703639304675e-05,
"loss": 3.4632,
"step": 1578496
},
{
"epoch": 0.02,
"learning_rate": 2.4149317691794155e-05,
"loss": 3.4668,
"step": 1579008
},
{
"epoch": 0.02,
"learning_rate": 2.4140948123087368e-05,
"loss": 3.4721,
"step": 1579520
},
{
"epoch": 0.02,
"learning_rate": 2.4132562175576844e-05,
"loss": 3.4544,
"step": 1580032
},
{
"epoch": 0.02,
"learning_rate": 2.4124176228066324e-05,
"loss": 3.4687,
"step": 1580544
},
{
"epoch": 0.02,
"learning_rate": 2.4115790280555804e-05,
"loss": 3.4626,
"step": 1581056
},
{
"epoch": 0.02,
"learning_rate": 2.410742071184902e-05,
"loss": 3.4719,
"step": 1581568
},
{
"epoch": 0.02,
"learning_rate": 2.4099034764338497e-05,
"loss": 3.4527,
"step": 1582080
},
{
"epoch": 0.02,
"learning_rate": 2.4090648816827977e-05,
"loss": 3.4758,
"step": 1582592
},
{
"epoch": 0.02,
"learning_rate": 2.4082262869317457e-05,
"loss": 3.4633,
"step": 1583104
},
{
"epoch": 0.02,
"learning_rate": 2.407389330061067e-05,
"loss": 3.4741,
"step": 1583616
},
{
"epoch": 0.02,
"learning_rate": 2.406550735310015e-05,
"loss": 3.4657,
"step": 1584128
},
{
"epoch": 0.02,
"learning_rate": 2.405712140558963e-05,
"loss": 3.4609,
"step": 1584640
},
{
"epoch": 0.02,
"learning_rate": 2.404873545807911e-05,
"loss": 3.4749,
"step": 1585152
},
{
"epoch": 0.02,
"learning_rate": 2.4040365889372318e-05,
"loss": 3.4796,
"step": 1585664
},
{
"epoch": 0.02,
"learning_rate": 2.4031979941861798e-05,
"loss": 3.4688,
"step": 1586176
},
{
"epoch": 0.02,
"learning_rate": 2.4023593994351278e-05,
"loss": 3.4612,
"step": 1586688
},
{
"epoch": 0.02,
"learning_rate": 2.4015208046840758e-05,
"loss": 3.4683,
"step": 1587200
},
{
"epoch": 0.02,
"learning_rate": 2.400683847813397e-05,
"loss": 3.4703,
"step": 1587712
},
{
"epoch": 0.02,
"learning_rate": 2.399845253062345e-05,
"loss": 3.459,
"step": 1588224
},
{
"epoch": 0.02,
"learning_rate": 2.399006658311293e-05,
"loss": 3.4652,
"step": 1588736
},
{
"epoch": 0.02,
"learning_rate": 2.398168063560241e-05,
"loss": 3.461,
"step": 1589248
},
{
"epoch": 0.02,
"learning_rate": 2.397331106689562e-05,
"loss": 3.4682,
"step": 1589760
},
{
"epoch": 0.02,
"learning_rate": 2.39649251193851e-05,
"loss": 3.4658,
"step": 1590272
},
{
"epoch": 0.02,
"learning_rate": 2.3956539171874583e-05,
"loss": 3.4716,
"step": 1590784
},
{
"epoch": 0.02,
"learning_rate": 2.3948153224364063e-05,
"loss": 3.4536,
"step": 1591296
},
{
"epoch": 0.02,
"learning_rate": 2.3939783655657272e-05,
"loss": 3.4661,
"step": 1591808
},
{
"epoch": 0.02,
"learning_rate": 2.393139770814675e-05,
"loss": 3.4647,
"step": 1592320
},
{
"epoch": 0.02,
"learning_rate": 2.392301176063623e-05,
"loss": 3.4769,
"step": 1592832
},
{
"epoch": 0.02,
"learning_rate": 2.391462581312571e-05,
"loss": 3.4704,
"step": 1593344
},
{
"epoch": 0.02,
"learning_rate": 2.3906256244418924e-05,
"loss": 3.474,
"step": 1593856
},
{
"epoch": 0.02,
"learning_rate": 2.3897870296908404e-05,
"loss": 3.4555,
"step": 1594368
},
{
"epoch": 0.02,
"learning_rate": 2.3889484349397884e-05,
"loss": 3.4725,
"step": 1594880
},
{
"epoch": 0.02,
"learning_rate": 2.3881098401887364e-05,
"loss": 3.4726,
"step": 1595392
},
{
"epoch": 0.02,
"learning_rate": 2.3872728833180573e-05,
"loss": 3.4746,
"step": 1595904
},
{
"epoch": 0.02,
"learning_rate": 2.3864342885670053e-05,
"loss": 3.4542,
"step": 1596416
},
{
"epoch": 0.02,
"learning_rate": 2.3855956938159536e-05,
"loss": 3.4755,
"step": 1596928
},
{
"epoch": 0.02,
"learning_rate": 2.3847570990649016e-05,
"loss": 3.4746,
"step": 1597440
},
{
"epoch": 0.02,
"learning_rate": 2.3839201421942225e-05,
"loss": 3.4921,
"step": 1597952
},
{
"epoch": 0.02,
"learning_rate": 2.3830815474431705e-05,
"loss": 3.4621,
"step": 1598464
},
{
"epoch": 0.02,
"learning_rate": 2.3822429526921185e-05,
"loss": 3.4708,
"step": 1598976
},
{
"epoch": 0.02,
"learning_rate": 2.3814043579410665e-05,
"loss": 3.472,
"step": 1599488
},
{
"epoch": 0.02,
"learning_rate": 2.3805674010703878e-05,
"loss": 3.4609,
"step": 1600000
},
{
"epoch": 0.02,
"learning_rate": 2.3797288063193358e-05,
"loss": 3.4738,
"step": 1600512
},
{
"epoch": 0.02,
"learning_rate": 2.3788902115682838e-05,
"loss": 3.4791,
"step": 1601024
},
{
"epoch": 0.02,
"learning_rate": 2.3780516168172318e-05,
"loss": 3.4735,
"step": 1601536
},
{
"epoch": 0.02,
"learning_rate": 2.3772146599465527e-05,
"loss": 3.4616,
"step": 1602048
},
{
"epoch": 0.02,
"learning_rate": 2.3763760651955007e-05,
"loss": 3.4688,
"step": 1602560
},
{
"epoch": 0.03,
"eval_loss": 3.8548104763031006,
"eval_runtime": 563.2617,
"eval_samples_per_second": 677.467,
"eval_steps_per_second": 21.171,
"step": 1602720
},
{
"epoch": 0.0,
"learning_rate": 2.375537470444449e-05,
"loss": 3.4564,
"step": 1603072
},
{
"epoch": 0.0,
"learning_rate": 2.374698875693397e-05,
"loss": 3.4574,
"step": 1603584
},
{
"epoch": 0.0,
"learning_rate": 2.3738602809423447e-05,
"loss": 3.473,
"step": 1604096
},
{
"epoch": 0.0,
"learning_rate": 2.3730216861912926e-05,
"loss": 3.4688,
"step": 1604608
},
{
"epoch": 0.0,
"learning_rate": 2.372184729320614e-05,
"loss": 3.4772,
"step": 1605120
},
{
"epoch": 0.0,
"learning_rate": 2.371346134569562e-05,
"loss": 3.4654,
"step": 1605632
},
{
"epoch": 0.0,
"learning_rate": 2.37050753981851e-05,
"loss": 3.4614,
"step": 1606144
},
{
"epoch": 0.0,
"learning_rate": 2.369668945067458e-05,
"loss": 3.4523,
"step": 1606656
},
{
"epoch": 0.0,
"learning_rate": 2.368831988196779e-05,
"loss": 3.4662,
"step": 1607168
},
{
"epoch": 0.0,
"learning_rate": 2.3679933934457268e-05,
"loss": 3.4667,
"step": 1607680
},
{
"epoch": 0.0,
"learning_rate": 2.3671547986946748e-05,
"loss": 3.4676,
"step": 1608192
},
{
"epoch": 0.0,
"learning_rate": 2.3663162039436228e-05,
"loss": 3.4749,
"step": 1608704
},
{
"epoch": 0.0,
"learning_rate": 2.3654808849533173e-05,
"loss": 3.4637,
"step": 1609216
},
{
"epoch": 0.0,
"learning_rate": 2.3646422902022653e-05,
"loss": 3.4613,
"step": 1609728
},
{
"epoch": 0.0,
"learning_rate": 2.3638036954512133e-05,
"loss": 3.4606,
"step": 1610240
},
{
"epoch": 0.0,
"learning_rate": 2.3629651007001613e-05,
"loss": 3.4501,
"step": 1610752
},
{
"epoch": 0.0,
"learning_rate": 2.3621265059491093e-05,
"loss": 3.4595,
"step": 1611264
},
{
"epoch": 0.0,
"learning_rate": 2.361287911198057e-05,
"loss": 3.4607,
"step": 1611776
},
{
"epoch": 0.0,
"learning_rate": 2.3604493164470053e-05,
"loss": 3.4558,
"step": 1612288
},
{
"epoch": 0.0,
"learning_rate": 2.3596107216959533e-05,
"loss": 3.4778,
"step": 1612800
},
{
"epoch": 0.0,
"learning_rate": 2.358773764825274e-05,
"loss": 3.4693,
"step": 1613312
},
{
"epoch": 0.0,
"learning_rate": 2.357935170074222e-05,
"loss": 3.4669,
"step": 1613824
},
{
"epoch": 0.0,
"learning_rate": 2.35709657532317e-05,
"loss": 3.4698,
"step": 1614336
},
{
"epoch": 0.0,
"learning_rate": 2.356257980572118e-05,
"loss": 3.4765,
"step": 1614848
},
{
"epoch": 0.0,
"learning_rate": 2.3554210237014394e-05,
"loss": 3.4536,
"step": 1615360
},
{
"epoch": 0.0,
"learning_rate": 2.3545824289503874e-05,
"loss": 3.4645,
"step": 1615872
},
{
"epoch": 0.0,
"learning_rate": 2.3537438341993354e-05,
"loss": 3.4697,
"step": 1616384
},
{
"epoch": 0.0,
"learning_rate": 2.3529052394482834e-05,
"loss": 3.4595,
"step": 1616896
},
{
"epoch": 0.0,
"learning_rate": 2.3520682825776043e-05,
"loss": 3.4543,
"step": 1617408
},
{
"epoch": 0.0,
"learning_rate": 2.3512296878265523e-05,
"loss": 3.4517,
"step": 1617920
},
{
"epoch": 0.01,
"learning_rate": 2.3503910930755006e-05,
"loss": 3.4699,
"step": 1618432
},
{
"epoch": 0.01,
"learning_rate": 2.3495524983244486e-05,
"loss": 3.4684,
"step": 1618944
},
{
"epoch": 0.01,
"learning_rate": 2.3487155414537695e-05,
"loss": 3.4669,
"step": 1619456
},
{
"epoch": 0.01,
"learning_rate": 2.3478769467027175e-05,
"loss": 3.4697,
"step": 1619968
},
{
"epoch": 0.01,
"learning_rate": 2.3470383519516655e-05,
"loss": 3.4582,
"step": 1620480
},
{
"epoch": 0.01,
"learning_rate": 2.3461997572006135e-05,
"loss": 3.4654,
"step": 1620992
},
{
"epoch": 0.01,
"learning_rate": 2.3453628003299348e-05,
"loss": 3.4583,
"step": 1621504
},
{
"epoch": 0.01,
"learning_rate": 2.3445242055788828e-05,
"loss": 3.4657,
"step": 1622016
},
{
"epoch": 0.01,
"learning_rate": 2.3436856108278308e-05,
"loss": 3.4504,
"step": 1622528
},
{
"epoch": 0.01,
"learning_rate": 2.3428470160767787e-05,
"loss": 3.4526,
"step": 1623040
},
{
"epoch": 0.01,
"learning_rate": 2.3420100592060997e-05,
"loss": 3.4574,
"step": 1623552
},
{
"epoch": 0.01,
"learning_rate": 2.3411714644550477e-05,
"loss": 3.4748,
"step": 1624064
},
{
"epoch": 0.01,
"learning_rate": 2.340332869703996e-05,
"loss": 3.4625,
"step": 1624576
},
{
"epoch": 0.01,
"learning_rate": 2.339494274952944e-05,
"loss": 3.4629,
"step": 1625088
},
{
"epoch": 0.01,
"learning_rate": 2.338657318082265e-05,
"loss": 3.4698,
"step": 1625600
},
{
"epoch": 0.01,
"learning_rate": 2.337818723331213e-05,
"loss": 3.4638,
"step": 1626112
},
{
"epoch": 0.01,
"learning_rate": 2.336980128580161e-05,
"loss": 3.4678,
"step": 1626624
},
{
"epoch": 0.01,
"learning_rate": 2.336141533829109e-05,
"loss": 3.4533,
"step": 1627136
},
{
"epoch": 0.01,
"learning_rate": 2.33530457695843e-05,
"loss": 3.4519,
"step": 1627648
},
{
"epoch": 0.01,
"learning_rate": 2.334465982207378e-05,
"loss": 3.4678,
"step": 1628160
},
{
"epoch": 0.01,
"learning_rate": 2.333627387456326e-05,
"loss": 3.4663,
"step": 1628672
},
{
"epoch": 0.01,
"learning_rate": 2.332788792705274e-05,
"loss": 3.4542,
"step": 1629184
},
{
"epoch": 0.01,
"learning_rate": 2.331951835834595e-05,
"loss": 3.4565,
"step": 1629696
},
{
"epoch": 0.01,
"learning_rate": 2.331113241083543e-05,
"loss": 3.4597,
"step": 1630208
},
{
"epoch": 0.01,
"learning_rate": 2.3302746463324914e-05,
"loss": 3.444,
"step": 1630720
},
{
"epoch": 0.01,
"learning_rate": 2.3294360515814394e-05,
"loss": 3.4639,
"step": 1631232
},
{
"epoch": 0.01,
"learning_rate": 2.3285990947107603e-05,
"loss": 3.4542,
"step": 1631744
},
{
"epoch": 0.01,
"learning_rate": 2.3277604999597083e-05,
"loss": 3.4597,
"step": 1632256
},
{
"epoch": 0.01,
"learning_rate": 2.3269219052086563e-05,
"loss": 3.4662,
"step": 1632768
},
{
"epoch": 0.01,
"learning_rate": 2.3260833104576042e-05,
"loss": 3.4561,
"step": 1633280
},
{
"epoch": 0.01,
"learning_rate": 2.3252463535869255e-05,
"loss": 3.4552,
"step": 1633792
},
{
"epoch": 0.01,
"learning_rate": 2.3244077588358735e-05,
"loss": 3.4572,
"step": 1634304
},
{
"epoch": 0.01,
"learning_rate": 2.3235691640848215e-05,
"loss": 3.4506,
"step": 1634816
},
{
"epoch": 0.01,
"learning_rate": 2.322730569333769e-05,
"loss": 3.4543,
"step": 1635328
},
{
"epoch": 0.01,
"learning_rate": 2.3218936124630904e-05,
"loss": 3.4645,
"step": 1635840
},
{
"epoch": 0.01,
"learning_rate": 2.3210550177120384e-05,
"loss": 3.4559,
"step": 1636352
},
{
"epoch": 0.01,
"learning_rate": 2.3202164229609867e-05,
"loss": 3.4489,
"step": 1636864
},
{
"epoch": 0.01,
"learning_rate": 2.3193778282099344e-05,
"loss": 3.4462,
"step": 1637376
},
{
"epoch": 0.01,
"learning_rate": 2.3185408713392556e-05,
"loss": 3.4464,
"step": 1637888
},
{
"epoch": 0.01,
"learning_rate": 2.3177022765882036e-05,
"loss": 3.4574,
"step": 1638400
},
{
"epoch": 0.01,
"learning_rate": 2.3168636818371516e-05,
"loss": 3.4655,
"step": 1638912
},
{
"epoch": 0.01,
"learning_rate": 2.3160250870860993e-05,
"loss": 3.4589,
"step": 1639424
},
{
"epoch": 0.01,
"learning_rate": 2.315188130215421e-05,
"loss": 3.4659,
"step": 1639936
},
{
"epoch": 0.01,
"learning_rate": 2.314349535464369e-05,
"loss": 3.4663,
"step": 1640448
},
{
"epoch": 0.01,
"learning_rate": 2.3135109407133165e-05,
"loss": 3.4727,
"step": 1640960
},
{
"epoch": 0.01,
"learning_rate": 2.3126723459622645e-05,
"loss": 3.4467,
"step": 1641472
},
{
"epoch": 0.01,
"learning_rate": 2.3118353890915858e-05,
"loss": 3.4591,
"step": 1641984
},
{
"epoch": 0.01,
"learning_rate": 2.3109967943405338e-05,
"loss": 3.4631,
"step": 1642496
},
{
"epoch": 0.01,
"learning_rate": 2.3101581995894818e-05,
"loss": 3.4486,
"step": 1643008
},
{
"epoch": 0.01,
"learning_rate": 2.3093196048384297e-05,
"loss": 3.4647,
"step": 1643520
},
{
"epoch": 0.01,
"learning_rate": 2.308482647967751e-05,
"loss": 3.4594,
"step": 1644032
},
{
"epoch": 0.01,
"learning_rate": 2.307644053216699e-05,
"loss": 3.4681,
"step": 1644544
},
{
"epoch": 0.01,
"learning_rate": 2.3068054584656466e-05,
"loss": 3.4576,
"step": 1645056
},
{
"epoch": 0.01,
"learning_rate": 2.3059668637145946e-05,
"loss": 3.4414,
"step": 1645568
},
{
"epoch": 0.01,
"learning_rate": 2.3051299068439162e-05,
"loss": 3.4516,
"step": 1646080
},
{
"epoch": 0.01,
"learning_rate": 2.304291312092864e-05,
"loss": 3.4534,
"step": 1646592
},
{
"epoch": 0.01,
"learning_rate": 2.303452717341812e-05,
"loss": 3.4612,
"step": 1647104
},
{
"epoch": 0.01,
"learning_rate": 2.30261412259076e-05,
"loss": 3.4576,
"step": 1647616
},
{
"epoch": 0.01,
"learning_rate": 2.301777165720081e-05,
"loss": 3.4646,
"step": 1648128
},
{
"epoch": 0.02,
"learning_rate": 2.300938570969029e-05,
"loss": 3.4626,
"step": 1648640
},
{
"epoch": 0.02,
"learning_rate": 2.300099976217977e-05,
"loss": 3.4522,
"step": 1649152
},
{
"epoch": 0.02,
"learning_rate": 2.299261381466925e-05,
"loss": 3.4463,
"step": 1649664
},
{
"epoch": 0.02,
"learning_rate": 2.2984244245962464e-05,
"loss": 3.4548,
"step": 1650176
},
{
"epoch": 0.02,
"learning_rate": 2.297585829845194e-05,
"loss": 3.469,
"step": 1650688
},
{
"epoch": 0.02,
"learning_rate": 2.296747235094142e-05,
"loss": 3.4602,
"step": 1651200
},
{
"epoch": 0.02,
"learning_rate": 2.29590864034309e-05,
"loss": 3.4651,
"step": 1651712
},
{
"epoch": 0.02,
"learning_rate": 2.2950716834724113e-05,
"loss": 3.449,
"step": 1652224
},
{
"epoch": 0.02,
"learning_rate": 2.2942330887213593e-05,
"loss": 3.4613,
"step": 1652736
},
{
"epoch": 0.02,
"learning_rate": 2.2933944939703072e-05,
"loss": 3.4626,
"step": 1653248
},
{
"epoch": 0.02,
"learning_rate": 2.2925558992192552e-05,
"loss": 3.4639,
"step": 1653760
},
{
"epoch": 0.02,
"learning_rate": 2.291718942348576e-05,
"loss": 3.4555,
"step": 1654272
},
{
"epoch": 0.02,
"learning_rate": 2.2908803475975245e-05,
"loss": 3.4531,
"step": 1654784
},
{
"epoch": 0.02,
"learning_rate": 2.2900417528464725e-05,
"loss": 3.4543,
"step": 1655296
},
{
"epoch": 0.02,
"learning_rate": 2.2892031580954205e-05,
"loss": 3.4617,
"step": 1655808
},
{
"epoch": 0.02,
"learning_rate": 2.2883662012247414e-05,
"loss": 3.4413,
"step": 1656320
},
{
"epoch": 0.02,
"learning_rate": 2.2875276064736894e-05,
"loss": 3.4581,
"step": 1656832
},
{
"epoch": 0.02,
"learning_rate": 2.2866890117226374e-05,
"loss": 3.4492,
"step": 1657344
},
{
"epoch": 0.02,
"learning_rate": 2.2858520548519586e-05,
"loss": 3.4624,
"step": 1657856
},
{
"epoch": 0.02,
"learning_rate": 2.2850134601009066e-05,
"loss": 3.4406,
"step": 1658368
},
{
"epoch": 0.02,
"learning_rate": 2.2841748653498546e-05,
"loss": 3.4687,
"step": 1658880
},
{
"epoch": 0.02,
"learning_rate": 2.2833362705988026e-05,
"loss": 3.4519,
"step": 1659392
},
{
"epoch": 0.02,
"learning_rate": 2.2824993137281235e-05,
"loss": 3.4638,
"step": 1659904
},
{
"epoch": 0.02,
"learning_rate": 2.2816607189770715e-05,
"loss": 3.4545,
"step": 1660416
},
{
"epoch": 0.02,
"learning_rate": 2.28082212422602e-05,
"loss": 3.4508,
"step": 1660928
},
{
"epoch": 0.02,
"learning_rate": 2.279983529474968e-05,
"loss": 3.46,
"step": 1661440
},
{
"epoch": 0.02,
"learning_rate": 2.2791465726042888e-05,
"loss": 3.4686,
"step": 1661952
},
{
"epoch": 0.02,
"learning_rate": 2.2783079778532368e-05,
"loss": 3.4571,
"step": 1662464
},
{
"epoch": 0.02,
"learning_rate": 2.2774693831021848e-05,
"loss": 3.4471,
"step": 1662976
},
{
"epoch": 0.02,
"learning_rate": 2.2766307883511327e-05,
"loss": 3.4578,
"step": 1663488
},
{
"epoch": 0.02,
"learning_rate": 2.275793831480454e-05,
"loss": 3.4616,
"step": 1664000
},
{
"epoch": 0.02,
"learning_rate": 2.274955236729402e-05,
"loss": 3.4478,
"step": 1664512
},
{
"epoch": 0.02,
"learning_rate": 2.27411664197835e-05,
"loss": 3.4558,
"step": 1665024
},
{
"epoch": 0.02,
"learning_rate": 2.273278047227298e-05,
"loss": 3.4478,
"step": 1665536
},
{
"epoch": 0.02,
"learning_rate": 2.272441090356619e-05,
"loss": 3.4565,
"step": 1666048
},
{
"epoch": 0.02,
"learning_rate": 2.271602495605567e-05,
"loss": 3.4574,
"step": 1666560
},
{
"epoch": 0.02,
"learning_rate": 2.2707639008545152e-05,
"loss": 3.462,
"step": 1667072
},
{
"epoch": 0.02,
"learning_rate": 2.2699253061034632e-05,
"loss": 3.4406,
"step": 1667584
},
{
"epoch": 0.02,
"learning_rate": 2.269088349232784e-05,
"loss": 3.4553,
"step": 1668096
},
{
"epoch": 0.02,
"learning_rate": 2.268249754481732e-05,
"loss": 3.4527,
"step": 1668608
},
{
"epoch": 0.02,
"learning_rate": 2.26741115973068e-05,
"loss": 3.4651,
"step": 1669120
},
{
"epoch": 0.02,
"learning_rate": 2.266572564979628e-05,
"loss": 3.4601,
"step": 1669632
},
{
"epoch": 0.02,
"learning_rate": 2.265733970228576e-05,
"loss": 3.4656,
"step": 1670144
},
{
"epoch": 0.02,
"learning_rate": 2.2648970133578974e-05,
"loss": 3.4465,
"step": 1670656
},
{
"epoch": 0.02,
"learning_rate": 2.2640584186068454e-05,
"loss": 3.4628,
"step": 1671168
},
{
"epoch": 0.02,
"learning_rate": 2.2632198238557933e-05,
"loss": 3.4612,
"step": 1671680
},
{
"epoch": 0.02,
"learning_rate": 2.2623828669851143e-05,
"loss": 3.4612,
"step": 1672192
},
{
"epoch": 0.02,
"learning_rate": 2.2615442722340623e-05,
"loss": 3.4504,
"step": 1672704
},
{
"epoch": 0.02,
"learning_rate": 2.2607056774830106e-05,
"loss": 3.459,
"step": 1673216
},
{
"epoch": 0.02,
"learning_rate": 2.2598670827319586e-05,
"loss": 3.4637,
"step": 1673728
},
{
"epoch": 0.02,
"learning_rate": 2.2590301258612795e-05,
"loss": 3.478,
"step": 1674240
},
{
"epoch": 0.02,
"learning_rate": 2.2581915311102275e-05,
"loss": 3.4514,
"step": 1674752
},
{
"epoch": 0.02,
"learning_rate": 2.2573529363591755e-05,
"loss": 3.4602,
"step": 1675264
},
{
"epoch": 0.02,
"learning_rate": 2.2565143416081235e-05,
"loss": 3.4598,
"step": 1675776
},
{
"epoch": 0.02,
"learning_rate": 2.2556773847374447e-05,
"loss": 3.4502,
"step": 1676288
},
{
"epoch": 0.02,
"learning_rate": 2.2548387899863927e-05,
"loss": 3.462,
"step": 1676800
},
{
"epoch": 0.02,
"learning_rate": 2.2540001952353407e-05,
"loss": 3.4617,
"step": 1677312
},
{
"epoch": 0.02,
"learning_rate": 2.2531616004842887e-05,
"loss": 3.4677,
"step": 1677824
},
{
"epoch": 0.02,
"learning_rate": 2.2523246436136096e-05,
"loss": 3.448,
"step": 1678336
},
{
"epoch": 0.02,
"learning_rate": 2.2514860488625576e-05,
"loss": 3.457,
"step": 1678848
},
{
"epoch": 0.03,
"eval_loss": 3.855649709701538,
"eval_runtime": 315.4362,
"eval_samples_per_second": 1209.725,
"eval_steps_per_second": 37.805,
"step": 1679040
},
{
"epoch": 0.0,
"learning_rate": 2.250647454111506e-05,
"loss": 3.4492,
"step": 1679360
},
{
"epoch": 0.0,
"learning_rate": 2.2498088593604536e-05,
"loss": 3.4413,
"step": 1679872
},
{
"epoch": 0.0,
"learning_rate": 2.2489702646094016e-05,
"loss": 3.4613,
"step": 1680384
},
{
"epoch": 0.0,
"learning_rate": 2.2481316698583496e-05,
"loss": 3.4601,
"step": 1680896
},
{
"epoch": 0.0,
"learning_rate": 2.247294712987671e-05,
"loss": 3.4647,
"step": 1681408
},
{
"epoch": 0.0,
"learning_rate": 2.2464561182366185e-05,
"loss": 3.4543,
"step": 1681920
},
{
"epoch": 0.0,
"learning_rate": 2.245617523485567e-05,
"loss": 3.4433,
"step": 1682432
},
{
"epoch": 0.0,
"learning_rate": 2.244778928734515e-05,
"loss": 3.4446,
"step": 1682944
},
{
"epoch": 0.0,
"learning_rate": 2.243941971863836e-05,
"loss": 3.4523,
"step": 1683456
},
{
"epoch": 0.0,
"learning_rate": 2.2431033771127837e-05,
"loss": 3.4544,
"step": 1683968
},
{
"epoch": 0.0,
"learning_rate": 2.2422647823617317e-05,
"loss": 3.4571,
"step": 1684480
},
{
"epoch": 0.0,
"learning_rate": 2.2414261876106797e-05,
"loss": 3.4642,
"step": 1684992
},
{
"epoch": 0.0,
"learning_rate": 2.2405908686203742e-05,
"loss": 3.4562,
"step": 1685504
},
{
"epoch": 0.0,
"learning_rate": 2.2397522738693222e-05,
"loss": 3.4471,
"step": 1686016
},
{
"epoch": 0.0,
"learning_rate": 2.2389136791182702e-05,
"loss": 3.4509,
"step": 1686528
},
{
"epoch": 0.0,
"learning_rate": 2.2380750843672182e-05,
"loss": 3.439,
"step": 1687040
},
{
"epoch": 0.0,
"learning_rate": 2.237236489616166e-05,
"loss": 3.4487,
"step": 1687552
},
{
"epoch": 0.0,
"learning_rate": 2.236397894865114e-05,
"loss": 3.4497,
"step": 1688064
},
{
"epoch": 0.0,
"learning_rate": 2.2355593001140622e-05,
"loss": 3.4451,
"step": 1688576
},
{
"epoch": 0.0,
"learning_rate": 2.2347207053630102e-05,
"loss": 3.4639,
"step": 1689088
},
{
"epoch": 0.0,
"learning_rate": 2.233883748492331e-05,
"loss": 3.4547,
"step": 1689600
},
{
"epoch": 0.0,
"learning_rate": 2.233045153741279e-05,
"loss": 3.458,
"step": 1690112
},
{
"epoch": 0.0,
"learning_rate": 2.232206558990227e-05,
"loss": 3.4558,
"step": 1690624
},
{
"epoch": 0.0,
"learning_rate": 2.231367964239175e-05,
"loss": 3.4645,
"step": 1691136
},
{
"epoch": 0.0,
"learning_rate": 2.2305310073684963e-05,
"loss": 3.4465,
"step": 1691648
},
{
"epoch": 0.0,
"learning_rate": 2.2296924126174443e-05,
"loss": 3.4569,
"step": 1692160
},
{
"epoch": 0.0,
"learning_rate": 2.2288538178663923e-05,
"loss": 3.4539,
"step": 1692672
},
{
"epoch": 0.0,
"learning_rate": 2.2280152231153403e-05,
"loss": 3.4501,
"step": 1693184
},
{
"epoch": 0.0,
"learning_rate": 2.2271782662446612e-05,
"loss": 3.4478,
"step": 1693696
},
{
"epoch": 0.0,
"learning_rate": 2.2263396714936092e-05,
"loss": 3.437,
"step": 1694208
},
{
"epoch": 0.01,
"learning_rate": 2.2255010767425576e-05,
"loss": 3.4614,
"step": 1694720
},
{
"epoch": 0.01,
"learning_rate": 2.2246641198718785e-05,
"loss": 3.4559,
"step": 1695232
},
{
"epoch": 0.01,
"learning_rate": 2.2238255251208265e-05,
"loss": 3.454,
"step": 1695744
},
{
"epoch": 0.01,
"learning_rate": 2.2229869303697745e-05,
"loss": 3.4584,
"step": 1696256
},
{
"epoch": 0.01,
"learning_rate": 2.2221483356187225e-05,
"loss": 3.4464,
"step": 1696768
},
{
"epoch": 0.01,
"learning_rate": 2.2213113787480437e-05,
"loss": 3.4526,
"step": 1697280
},
{
"epoch": 0.01,
"learning_rate": 2.2204727839969917e-05,
"loss": 3.4522,
"step": 1697792
},
{
"epoch": 0.01,
"learning_rate": 2.2196341892459397e-05,
"loss": 3.4483,
"step": 1698304
},
{
"epoch": 0.01,
"learning_rate": 2.2187955944948877e-05,
"loss": 3.441,
"step": 1698816
},
{
"epoch": 0.01,
"learning_rate": 2.2179586376242086e-05,
"loss": 3.4419,
"step": 1699328
},
{
"epoch": 0.01,
"learning_rate": 2.2171200428731566e-05,
"loss": 3.4441,
"step": 1699840
},
{
"epoch": 0.01,
"learning_rate": 2.2162814481221046e-05,
"loss": 3.4638,
"step": 1700352
},
{
"epoch": 0.01,
"learning_rate": 2.215442853371053e-05,
"loss": 3.4495,
"step": 1700864
},
{
"epoch": 0.01,
"learning_rate": 2.214605896500374e-05,
"loss": 3.448,
"step": 1701376
},
{
"epoch": 0.01,
"learning_rate": 2.213767301749322e-05,
"loss": 3.4629,
"step": 1701888
},
{
"epoch": 0.01,
"learning_rate": 2.21292870699827e-05,
"loss": 3.451,
"step": 1702400
},
{
"epoch": 0.01,
"learning_rate": 2.212090112247218e-05,
"loss": 3.4598,
"step": 1702912
},
{
"epoch": 0.01,
"learning_rate": 2.211253155376539e-05,
"loss": 3.4435,
"step": 1703424
},
{
"epoch": 0.01,
"learning_rate": 2.210414560625487e-05,
"loss": 3.4356,
"step": 1703936
},
{
"epoch": 0.01,
"learning_rate": 2.209575965874435e-05,
"loss": 3.4574,
"step": 1704448
},
{
"epoch": 0.01,
"learning_rate": 2.208737371123383e-05,
"loss": 3.4543,
"step": 1704960
},
{
"epoch": 0.01,
"learning_rate": 2.207900414252704e-05,
"loss": 3.4483,
"step": 1705472
},
{
"epoch": 0.01,
"learning_rate": 2.207061819501652e-05,
"loss": 3.444,
"step": 1705984
},
{
"epoch": 0.01,
"learning_rate": 2.2062232247506e-05,
"loss": 3.4495,
"step": 1706496
},
{
"epoch": 0.01,
"learning_rate": 2.2053846299995483e-05,
"loss": 3.4298,
"step": 1707008
},
{
"epoch": 0.01,
"learning_rate": 2.2045476731288692e-05,
"loss": 3.4552,
"step": 1707520
},
{
"epoch": 0.01,
"learning_rate": 2.2037090783778172e-05,
"loss": 3.4451,
"step": 1708032
},
{
"epoch": 0.01,
"learning_rate": 2.2028704836267652e-05,
"loss": 3.4463,
"step": 1708544
},
{
"epoch": 0.01,
"learning_rate": 2.2020318888757132e-05,
"loss": 3.4551,
"step": 1709056
},
{
"epoch": 0.01,
"learning_rate": 2.2011949320050345e-05,
"loss": 3.4441,
"step": 1709568
},
{
"epoch": 0.01,
"learning_rate": 2.2003563372539824e-05,
"loss": 3.4422,
"step": 1710080
},
{
"epoch": 0.01,
"learning_rate": 2.1995177425029304e-05,
"loss": 3.4474,
"step": 1710592
},
{
"epoch": 0.01,
"learning_rate": 2.1986791477518784e-05,
"loss": 3.4385,
"step": 1711104
},
{
"epoch": 0.01,
"learning_rate": 2.1978421908811994e-05,
"loss": 3.446,
"step": 1711616
},
{
"epoch": 0.01,
"learning_rate": 2.1970035961301473e-05,
"loss": 3.4522,
"step": 1712128
},
{
"epoch": 0.01,
"learning_rate": 2.1961650013790953e-05,
"loss": 3.4461,
"step": 1712640
},
{
"epoch": 0.01,
"learning_rate": 2.1953264066280433e-05,
"loss": 3.4391,
"step": 1713152
},
{
"epoch": 0.01,
"learning_rate": 2.1944894497573646e-05,
"loss": 3.4352,
"step": 1713664
},
{
"epoch": 0.01,
"learning_rate": 2.1936508550063126e-05,
"loss": 3.4334,
"step": 1714176
},
{
"epoch": 0.01,
"learning_rate": 2.1928122602552606e-05,
"loss": 3.4427,
"step": 1714688
},
{
"epoch": 0.01,
"learning_rate": 2.1919736655042082e-05,
"loss": 3.4531,
"step": 1715200
},
{
"epoch": 0.01,
"learning_rate": 2.1911367086335298e-05,
"loss": 3.4476,
"step": 1715712
},
{
"epoch": 0.01,
"learning_rate": 2.1902981138824778e-05,
"loss": 3.4554,
"step": 1716224
},
{
"epoch": 0.01,
"learning_rate": 2.1894595191314258e-05,
"loss": 3.4529,
"step": 1716736
},
{
"epoch": 0.01,
"learning_rate": 2.1886209243803735e-05,
"loss": 3.4637,
"step": 1717248
},
{
"epoch": 0.01,
"learning_rate": 2.1877839675096947e-05,
"loss": 3.4367,
"step": 1717760
},
{
"epoch": 0.01,
"learning_rate": 2.1869453727586427e-05,
"loss": 3.4528,
"step": 1718272
},
{
"epoch": 0.01,
"learning_rate": 2.1861067780075907e-05,
"loss": 3.4509,
"step": 1718784
},
{
"epoch": 0.01,
"learning_rate": 2.1852681832565387e-05,
"loss": 3.4329,
"step": 1719296
},
{
"epoch": 0.01,
"learning_rate": 2.18443122638586e-05,
"loss": 3.4524,
"step": 1719808
},
{
"epoch": 0.01,
"learning_rate": 2.183592631634808e-05,
"loss": 3.4507,
"step": 1720320
},
{
"epoch": 0.01,
"learning_rate": 2.1827540368837556e-05,
"loss": 3.4536,
"step": 1720832
},
{
"epoch": 0.01,
"learning_rate": 2.1819154421327036e-05,
"loss": 3.4481,
"step": 1721344
},
{
"epoch": 0.01,
"learning_rate": 2.181078485262025e-05,
"loss": 3.4313,
"step": 1721856
},
{
"epoch": 0.01,
"learning_rate": 2.1802398905109732e-05,
"loss": 3.4417,
"step": 1722368
},
{
"epoch": 0.01,
"learning_rate": 2.179401295759921e-05,
"loss": 3.4441,
"step": 1722880
},
{
"epoch": 0.01,
"learning_rate": 2.178562701008869e-05,
"loss": 3.4492,
"step": 1723392
},
{
"epoch": 0.01,
"learning_rate": 2.17772574413819e-05,
"loss": 3.4446,
"step": 1723904
},
{
"epoch": 0.01,
"learning_rate": 2.1768871493871377e-05,
"loss": 3.4531,
"step": 1724416
},
{
"epoch": 0.02,
"learning_rate": 2.176048554636086e-05,
"loss": 3.4498,
"step": 1724928
},
{
"epoch": 0.02,
"learning_rate": 2.175209959885034e-05,
"loss": 3.4453,
"step": 1725440
},
{
"epoch": 0.02,
"learning_rate": 2.1743730030143553e-05,
"loss": 3.4356,
"step": 1725952
},
{
"epoch": 0.02,
"learning_rate": 2.173534408263303e-05,
"loss": 3.4394,
"step": 1726464
},
{
"epoch": 0.02,
"learning_rate": 2.172695813512251e-05,
"loss": 3.4589,
"step": 1726976
},
{
"epoch": 0.02,
"learning_rate": 2.171857218761199e-05,
"loss": 3.452,
"step": 1727488
},
{
"epoch": 0.02,
"learning_rate": 2.1710202618905202e-05,
"loss": 3.4515,
"step": 1728000
},
{
"epoch": 0.02,
"learning_rate": 2.1701816671394682e-05,
"loss": 3.4376,
"step": 1728512
},
{
"epoch": 0.02,
"learning_rate": 2.1693430723884162e-05,
"loss": 3.4494,
"step": 1729024
},
{
"epoch": 0.02,
"learning_rate": 2.1685044776373642e-05,
"loss": 3.4523,
"step": 1729536
},
{
"epoch": 0.02,
"learning_rate": 2.167667520766685e-05,
"loss": 3.4508,
"step": 1730048
},
{
"epoch": 0.02,
"learning_rate": 2.166828926015633e-05,
"loss": 3.4474,
"step": 1730560
},
{
"epoch": 0.02,
"learning_rate": 2.1659903312645814e-05,
"loss": 3.4427,
"step": 1731072
},
{
"epoch": 0.02,
"learning_rate": 2.1651517365135294e-05,
"loss": 3.4439,
"step": 1731584
},
{
"epoch": 0.02,
"learning_rate": 2.1643147796428503e-05,
"loss": 3.4485,
"step": 1732096
},
{
"epoch": 0.02,
"learning_rate": 2.1634761848917983e-05,
"loss": 3.4329,
"step": 1732608
},
{
"epoch": 0.02,
"learning_rate": 2.1626375901407463e-05,
"loss": 3.4436,
"step": 1733120
},
{
"epoch": 0.02,
"learning_rate": 2.1617989953896943e-05,
"loss": 3.4378,
"step": 1733632
},
{
"epoch": 0.02,
"learning_rate": 2.1609620385190156e-05,
"loss": 3.4502,
"step": 1734144
},
{
"epoch": 0.02,
"learning_rate": 2.1601234437679636e-05,
"loss": 3.4329,
"step": 1734656
},
{
"epoch": 0.02,
"learning_rate": 2.1592848490169116e-05,
"loss": 3.4534,
"step": 1735168
},
{
"epoch": 0.02,
"learning_rate": 2.1584462542658596e-05,
"loss": 3.4415,
"step": 1735680
},
{
"epoch": 0.02,
"learning_rate": 2.1576092973951805e-05,
"loss": 3.4471,
"step": 1736192
},
{
"epoch": 0.02,
"learning_rate": 2.1567707026441285e-05,
"loss": 3.4497,
"step": 1736704
},
{
"epoch": 0.02,
"learning_rate": 2.1559321078930768e-05,
"loss": 3.4369,
"step": 1737216
},
{
"epoch": 0.02,
"learning_rate": 2.1550935131420248e-05,
"loss": 3.4489,
"step": 1737728
},
{
"epoch": 0.02,
"learning_rate": 2.1542565562713457e-05,
"loss": 3.4588,
"step": 1738240
},
{
"epoch": 0.02,
"learning_rate": 2.1534179615202937e-05,
"loss": 3.4448,
"step": 1738752
},
{
"epoch": 0.02,
"learning_rate": 2.1525793667692417e-05,
"loss": 3.4432,
"step": 1739264
},
{
"epoch": 0.02,
"learning_rate": 2.151742409898563e-05,
"loss": 3.4376,
"step": 1739776
},
{
"epoch": 0.02,
"learning_rate": 2.150903815147511e-05,
"loss": 3.4507,
"step": 1740288
},
{
"epoch": 0.02,
"learning_rate": 2.150065220396459e-05,
"loss": 3.4428,
"step": 1740800
},
{
"epoch": 0.02,
"learning_rate": 2.149226625645407e-05,
"loss": 3.4423,
"step": 1741312
},
{
"epoch": 0.02,
"learning_rate": 2.148388030894355e-05,
"loss": 3.4352,
"step": 1741824
},
{
"epoch": 0.02,
"learning_rate": 2.147551074023676e-05,
"loss": 3.4451,
"step": 1742336
},
{
"epoch": 0.02,
"learning_rate": 2.146712479272624e-05,
"loss": 3.4485,
"step": 1742848
},
{
"epoch": 0.02,
"learning_rate": 2.1458738845215722e-05,
"loss": 3.4488,
"step": 1743360
},
{
"epoch": 0.02,
"learning_rate": 2.1450352897705202e-05,
"loss": 3.4313,
"step": 1743872
},
{
"epoch": 0.02,
"learning_rate": 2.144198332899841e-05,
"loss": 3.4462,
"step": 1744384
},
{
"epoch": 0.02,
"learning_rate": 2.143359738148789e-05,
"loss": 3.4377,
"step": 1744896
},
{
"epoch": 0.02,
"learning_rate": 2.142521143397737e-05,
"loss": 3.4554,
"step": 1745408
},
{
"epoch": 0.02,
"learning_rate": 2.1416841865270583e-05,
"loss": 3.4457,
"step": 1745920
},
{
"epoch": 0.02,
"learning_rate": 2.1408455917760063e-05,
"loss": 3.4565,
"step": 1746432
},
{
"epoch": 0.02,
"learning_rate": 2.1400069970249543e-05,
"loss": 3.4339,
"step": 1746944
},
{
"epoch": 0.02,
"learning_rate": 2.1391684022739023e-05,
"loss": 3.4538,
"step": 1747456
},
{
"epoch": 0.02,
"learning_rate": 2.1383314454032232e-05,
"loss": 3.4483,
"step": 1747968
},
{
"epoch": 0.02,
"learning_rate": 2.1374928506521712e-05,
"loss": 3.4499,
"step": 1748480
},
{
"epoch": 0.02,
"learning_rate": 2.1366542559011192e-05,
"loss": 3.4349,
"step": 1748992
},
{
"epoch": 0.02,
"learning_rate": 2.1358156611500672e-05,
"loss": 3.4509,
"step": 1749504
},
{
"epoch": 0.02,
"learning_rate": 2.1349787042793885e-05,
"loss": 3.452,
"step": 1750016
},
{
"epoch": 0.02,
"learning_rate": 2.1341401095283364e-05,
"loss": 3.4667,
"step": 1750528
},
{
"epoch": 0.02,
"learning_rate": 2.1333015147772844e-05,
"loss": 3.4441,
"step": 1751040
},
{
"epoch": 0.02,
"learning_rate": 2.1324629200262324e-05,
"loss": 3.4482,
"step": 1751552
},
{
"epoch": 0.02,
"learning_rate": 2.1316259631555537e-05,
"loss": 3.452,
"step": 1752064
},
{
"epoch": 0.02,
"learning_rate": 2.1307873684045017e-05,
"loss": 3.4425,
"step": 1752576
},
{
"epoch": 0.02,
"learning_rate": 2.1299487736534497e-05,
"loss": 3.4477,
"step": 1753088
},
{
"epoch": 0.02,
"learning_rate": 2.1291101789023977e-05,
"loss": 3.4517,
"step": 1753600
},
{
"epoch": 0.02,
"learning_rate": 2.1282732220317186e-05,
"loss": 3.4535,
"step": 1754112
},
{
"epoch": 0.02,
"learning_rate": 2.1274346272806666e-05,
"loss": 3.4408,
"step": 1754624
},
{
"epoch": 0.02,
"learning_rate": 2.1265960325296146e-05,
"loss": 3.4477,
"step": 1755136
},
{
"epoch": 0.03,
"eval_loss": 3.8581430912017822,
"eval_runtime": 304.4616,
"eval_samples_per_second": 1253.33,
"eval_steps_per_second": 39.168,
"step": 1755360
},
{
"epoch": 1.0,
"learning_rate": 2.1257574377785626e-05,
"loss": 3.4424,
"step": 1755648
},
{
"epoch": 1.0,
"learning_rate": 2.1249204809078838e-05,
"loss": 3.432,
"step": 1756160
},
{
"epoch": 1.0,
"learning_rate": 2.1240818861568318e-05,
"loss": 3.4481,
"step": 1756672
},
{
"epoch": 1.0,
"learning_rate": 2.1232432914057798e-05,
"loss": 3.4499,
"step": 1757184
},
{
"epoch": 1.0,
"learning_rate": 2.1224046966547275e-05,
"loss": 3.4541,
"step": 1757696
},
{
"epoch": 1.0,
"learning_rate": 2.1215677397840487e-05,
"loss": 3.4444,
"step": 1758208
},
{
"epoch": 1.0,
"learning_rate": 2.120729145032997e-05,
"loss": 3.4367,
"step": 1758720
},
{
"epoch": 1.0,
"learning_rate": 2.119890550281945e-05,
"loss": 3.4343,
"step": 1759232
},
{
"epoch": 1.0,
"learning_rate": 2.1190519555308927e-05,
"loss": 3.4434,
"step": 1759744
},
{
"epoch": 1.0,
"learning_rate": 2.118214998660214e-05,
"loss": 3.4417,
"step": 1760256
},
{
"epoch": 1.0,
"learning_rate": 2.117376403909162e-05,
"loss": 3.4474,
"step": 1760768
},
{
"epoch": 1.0,
"learning_rate": 2.11653780915811e-05,
"loss": 3.452,
"step": 1761280
},
{
"epoch": 1.0,
"learning_rate": 2.1157008522874312e-05,
"loss": 3.4451,
"step": 1761792
},
{
"epoch": 1.0,
"learning_rate": 2.1148622575363792e-05,
"loss": 3.4373,
"step": 1762304
},
{
"epoch": 1.0,
"learning_rate": 2.1140236627853272e-05,
"loss": 3.4401,
"step": 1762816
},
{
"epoch": 1.0,
"learning_rate": 2.113185068034275e-05,
"loss": 3.4247,
"step": 1763328
},
{
"epoch": 1.0,
"learning_rate": 2.112346473283223e-05,
"loss": 3.4389,
"step": 1763840
},
{
"epoch": 1.0,
"learning_rate": 2.1115078785321708e-05,
"loss": 3.4399,
"step": 1764352
},
{
"epoch": 1.0,
"learning_rate": 2.110669283781119e-05,
"loss": 3.4387,
"step": 1764864
},
{
"epoch": 1.0,
"learning_rate": 2.109830689030067e-05,
"loss": 3.448,
"step": 1765376
},
{
"epoch": 1.0,
"learning_rate": 2.108993732159388e-05,
"loss": 3.451,
"step": 1765888
},
{
"epoch": 1.0,
"learning_rate": 2.108155137408336e-05,
"loss": 3.4446,
"step": 1766400
},
{
"epoch": 1.0,
"learning_rate": 2.107316542657284e-05,
"loss": 3.4481,
"step": 1766912
},
{
"epoch": 1.0,
"learning_rate": 2.106477947906232e-05,
"loss": 3.4509,
"step": 1767424
},
{
"epoch": 1.0,
"learning_rate": 2.1056409910355533e-05,
"loss": 3.4355,
"step": 1767936
},
{
"epoch": 1.0,
"learning_rate": 2.1048023962845013e-05,
"loss": 3.446,
"step": 1768448
},
{
"epoch": 1.0,
"learning_rate": 2.1039638015334493e-05,
"loss": 3.4449,
"step": 1768960
},
{
"epoch": 1.0,
"learning_rate": 2.1031252067823973e-05,
"loss": 3.4386,
"step": 1769472
},
{
"epoch": 1.0,
"learning_rate": 2.1022882499117182e-05,
"loss": 3.4339,
"step": 1769984
},
{
"epoch": 1.0,
"learning_rate": 2.1014496551606662e-05,
"loss": 3.4301,
"step": 1770496
},
{
"epoch": 1.01,
"learning_rate": 2.1006110604096145e-05,
"loss": 3.4462,
"step": 1771008
},
{
"epoch": 1.01,
"learning_rate": 2.0997724656585625e-05,
"loss": 3.4478,
"step": 1771520
},
{
"epoch": 1.01,
"learning_rate": 2.0989355087878834e-05,
"loss": 3.4437,
"step": 1772032
},
{
"epoch": 1.01,
"learning_rate": 2.0980969140368314e-05,
"loss": 3.4455,
"step": 1772544
},
{
"epoch": 1.01,
"learning_rate": 2.0972583192857794e-05,
"loss": 3.4333,
"step": 1773056
},
{
"epoch": 1.01,
"learning_rate": 2.0964197245347274e-05,
"loss": 3.4434,
"step": 1773568
},
{
"epoch": 1.01,
"learning_rate": 2.0955827676640487e-05,
"loss": 3.4468,
"step": 1774080
},
{
"epoch": 1.01,
"learning_rate": 2.0947441729129967e-05,
"loss": 3.4338,
"step": 1774592
},
{
"epoch": 1.01,
"learning_rate": 2.0939055781619447e-05,
"loss": 3.4363,
"step": 1775104
},
{
"epoch": 1.01,
"learning_rate": 2.0930669834108927e-05,
"loss": 3.4311,
"step": 1775616
},
{
"epoch": 1.01,
"learning_rate": 2.0922300265402136e-05,
"loss": 3.4336,
"step": 1776128
},
{
"epoch": 1.01,
"learning_rate": 2.0913914317891616e-05,
"loss": 3.4521,
"step": 1776640
},
{
"epoch": 1.01,
"learning_rate": 2.0905528370381096e-05,
"loss": 3.439,
"step": 1777152
},
{
"epoch": 1.01,
"learning_rate": 2.0897158801674308e-05,
"loss": 3.4329,
"step": 1777664
},
{
"epoch": 1.01,
"learning_rate": 2.0888772854163788e-05,
"loss": 3.4506,
"step": 1778176
},
{
"epoch": 1.01,
"learning_rate": 2.0880386906653268e-05,
"loss": 3.4445,
"step": 1778688
},
{
"epoch": 1.01,
"learning_rate": 2.0872000959142748e-05,
"loss": 3.4476,
"step": 1779200
},
{
"epoch": 1.01,
"learning_rate": 2.0863631390435957e-05,
"loss": 3.4324,
"step": 1779712
},
{
"epoch": 1.01,
"learning_rate": 2.085524544292544e-05,
"loss": 3.4255,
"step": 1780224
},
{
"epoch": 1.01,
"learning_rate": 2.084685949541492e-05,
"loss": 3.4511,
"step": 1780736
},
{
"epoch": 1.01,
"learning_rate": 2.08384735479044e-05,
"loss": 3.4418,
"step": 1781248
},
{
"epoch": 1.01,
"learning_rate": 2.083010397919761e-05,
"loss": 3.4391,
"step": 1781760
},
{
"epoch": 1.01,
"learning_rate": 2.082171803168709e-05,
"loss": 3.4386,
"step": 1782272
},
{
"epoch": 1.01,
"learning_rate": 2.081333208417657e-05,
"loss": 3.4306,
"step": 1782784
},
{
"epoch": 1.01,
"learning_rate": 2.080494613666605e-05,
"loss": 3.4231,
"step": 1783296
},
{
"epoch": 1.01,
"learning_rate": 2.079656018915553e-05,
"loss": 3.438,
"step": 1783808
},
{
"epoch": 1.01,
"learning_rate": 2.078819062044874e-05,
"loss": 3.4359,
"step": 1784320
},
{
"epoch": 1.01,
"learning_rate": 2.077980467293822e-05,
"loss": 3.4377,
"step": 1784832
},
{
"epoch": 1.01,
"learning_rate": 2.07714187254277e-05,
"loss": 3.4434,
"step": 1785344
},
{
"epoch": 1.01,
"learning_rate": 2.0763032777917178e-05,
"loss": 3.4336,
"step": 1785856
},
{
"epoch": 1.01,
"learning_rate": 2.0754663209210394e-05,
"loss": 3.4306,
"step": 1786368
},
{
"epoch": 1.01,
"learning_rate": 2.0746277261699874e-05,
"loss": 3.4415,
"step": 1786880
},
{
"epoch": 1.01,
"learning_rate": 2.073789131418935e-05,
"loss": 3.4256,
"step": 1787392
},
{
"epoch": 1.01,
"learning_rate": 2.0729521745482563e-05,
"loss": 3.435,
"step": 1787904
},
{
"epoch": 1.01,
"learning_rate": 2.0721135797972043e-05,
"loss": 3.4391,
"step": 1788416
},
{
"epoch": 1.01,
"learning_rate": 2.0712749850461523e-05,
"loss": 3.4353,
"step": 1788928
},
{
"epoch": 1.01,
"learning_rate": 2.0704363902951003e-05,
"loss": 3.4266,
"step": 1789440
},
{
"epoch": 1.01,
"learning_rate": 2.0695994334244215e-05,
"loss": 3.4272,
"step": 1789952
},
{
"epoch": 1.01,
"learning_rate": 2.0687608386733695e-05,
"loss": 3.422,
"step": 1790464
},
{
"epoch": 1.01,
"learning_rate": 2.0679222439223175e-05,
"loss": 3.434,
"step": 1790976
},
{
"epoch": 1.01,
"learning_rate": 2.0670836491712652e-05,
"loss": 3.4428,
"step": 1791488
},
{
"epoch": 1.01,
"learning_rate": 2.0662466923005864e-05,
"loss": 3.4389,
"step": 1792000
},
{
"epoch": 1.01,
"learning_rate": 2.0654080975495348e-05,
"loss": 3.4422,
"step": 1792512
},
{
"epoch": 1.01,
"learning_rate": 2.0645695027984824e-05,
"loss": 3.4429,
"step": 1793024
},
{
"epoch": 1.01,
"learning_rate": 2.0637309080474304e-05,
"loss": 3.4526,
"step": 1793536
},
{
"epoch": 1.01,
"learning_rate": 2.0628939511767517e-05,
"loss": 3.4251,
"step": 1794048
},
{
"epoch": 1.01,
"learning_rate": 2.0620553564256997e-05,
"loss": 3.4433,
"step": 1794560
},
{
"epoch": 1.01,
"learning_rate": 2.0612167616746477e-05,
"loss": 3.4399,
"step": 1795072
},
{
"epoch": 1.01,
"learning_rate": 2.0603781669235957e-05,
"loss": 3.4204,
"step": 1795584
},
{
"epoch": 1.01,
"learning_rate": 2.059541210052917e-05,
"loss": 3.4455,
"step": 1796096
},
{
"epoch": 1.01,
"learning_rate": 2.0587026153018646e-05,
"loss": 3.4359,
"step": 1796608
},
{
"epoch": 1.01,
"learning_rate": 2.0578640205508126e-05,
"loss": 3.4425,
"step": 1797120
},
{
"epoch": 1.01,
"learning_rate": 2.0570254257997606e-05,
"loss": 3.4399,
"step": 1797632
},
{
"epoch": 1.01,
"learning_rate": 2.0561884689290818e-05,
"loss": 3.4199,
"step": 1798144
},
{
"epoch": 1.01,
"learning_rate": 2.0553498741780298e-05,
"loss": 3.4276,
"step": 1798656
},
{
"epoch": 1.01,
"learning_rate": 2.0545112794269778e-05,
"loss": 3.4346,
"step": 1799168
},
{
"epoch": 1.01,
"learning_rate": 2.0536726846759258e-05,
"loss": 3.4381,
"step": 1799680
},
{
"epoch": 1.01,
"learning_rate": 2.052835727805247e-05,
"loss": 3.4365,
"step": 1800192
},
{
"epoch": 1.01,
"learning_rate": 2.0519971330541947e-05,
"loss": 3.4403,
"step": 1800704
},
{
"epoch": 1.02,
"learning_rate": 2.051158538303143e-05,
"loss": 3.4374,
"step": 1801216
},
{
"epoch": 1.02,
"learning_rate": 2.050319943552091e-05,
"loss": 3.4339,
"step": 1801728
},
{
"epoch": 1.02,
"learning_rate": 2.049482986681412e-05,
"loss": 3.4293,
"step": 1802240
},
{
"epoch": 1.02,
"learning_rate": 2.04864439193036e-05,
"loss": 3.4279,
"step": 1802752
},
{
"epoch": 1.02,
"learning_rate": 2.047805797179308e-05,
"loss": 3.4474,
"step": 1803264
},
{
"epoch": 1.02,
"learning_rate": 2.046967202428256e-05,
"loss": 3.4396,
"step": 1803776
},
{
"epoch": 1.02,
"learning_rate": 2.046130245557577e-05,
"loss": 3.4462,
"step": 1804288
},
{
"epoch": 1.02,
"learning_rate": 2.045291650806525e-05,
"loss": 3.4235,
"step": 1804800
},
{
"epoch": 1.02,
"learning_rate": 2.044453056055473e-05,
"loss": 3.4388,
"step": 1805312
},
{
"epoch": 1.02,
"learning_rate": 2.043614461304421e-05,
"loss": 3.4411,
"step": 1805824
},
{
"epoch": 1.02,
"learning_rate": 2.042777504433742e-05,
"loss": 3.4425,
"step": 1806336
},
{
"epoch": 1.02,
"learning_rate": 2.04193890968269e-05,
"loss": 3.4366,
"step": 1806848
},
{
"epoch": 1.02,
"learning_rate": 2.041100314931638e-05,
"loss": 3.432,
"step": 1807360
},
{
"epoch": 1.02,
"learning_rate": 2.0402617201805864e-05,
"loss": 3.4342,
"step": 1807872
},
{
"epoch": 1.02,
"learning_rate": 2.0394247633099073e-05,
"loss": 3.4376,
"step": 1808384
},
{
"epoch": 1.02,
"learning_rate": 2.0385861685588553e-05,
"loss": 3.4209,
"step": 1808896
},
{
"epoch": 1.02,
"learning_rate": 2.0377475738078033e-05,
"loss": 3.4357,
"step": 1809408
},
{
"epoch": 1.02,
"learning_rate": 2.0369089790567513e-05,
"loss": 3.4244,
"step": 1809920
},
{
"epoch": 1.02,
"learning_rate": 2.0360720221860725e-05,
"loss": 3.4424,
"step": 1810432
},
{
"epoch": 1.02,
"learning_rate": 2.0352334274350205e-05,
"loss": 3.4251,
"step": 1810944
},
{
"epoch": 1.02,
"learning_rate": 2.0343948326839685e-05,
"loss": 3.4379,
"step": 1811456
},
{
"epoch": 1.02,
"learning_rate": 2.0335562379329165e-05,
"loss": 3.4351,
"step": 1811968
},
{
"epoch": 1.02,
"learning_rate": 2.0327192810622374e-05,
"loss": 3.4393,
"step": 1812480
},
{
"epoch": 1.02,
"learning_rate": 2.0318806863111854e-05,
"loss": 3.4375,
"step": 1812992
},
{
"epoch": 1.02,
"learning_rate": 2.0310420915601334e-05,
"loss": 3.4267,
"step": 1813504
},
{
"epoch": 1.02,
"learning_rate": 2.0302034968090818e-05,
"loss": 3.4378,
"step": 1814016
},
{
"epoch": 1.02,
"learning_rate": 2.0293665399384027e-05,
"loss": 3.448,
"step": 1814528
},
{
"epoch": 1.02,
"learning_rate": 2.0285279451873507e-05,
"loss": 3.4339,
"step": 1815040
},
{
"epoch": 1.02,
"learning_rate": 2.0276893504362987e-05,
"loss": 3.4342,
"step": 1815552
},
{
"epoch": 1.02,
"learning_rate": 2.0268507556852467e-05,
"loss": 3.4264,
"step": 1816064
},
{
"epoch": 1.02,
"learning_rate": 2.026013798814568e-05,
"loss": 3.4366,
"step": 1816576
},
{
"epoch": 1.02,
"learning_rate": 2.025175204063516e-05,
"loss": 3.4364,
"step": 1817088
},
{
"epoch": 1.02,
"learning_rate": 2.024336609312464e-05,
"loss": 3.4276,
"step": 1817600
},
{
"epoch": 1.02,
"learning_rate": 2.023498014561412e-05,
"loss": 3.4289,
"step": 1818112
},
{
"epoch": 1.02,
"learning_rate": 2.0226610576907328e-05,
"loss": 3.4325,
"step": 1818624
},
{
"epoch": 1.02,
"learning_rate": 2.0218224629396808e-05,
"loss": 3.4374,
"step": 1819136
},
{
"epoch": 1.02,
"learning_rate": 2.0209838681886288e-05,
"loss": 3.4392,
"step": 1819648
},
{
"epoch": 1.02,
"learning_rate": 2.020145273437577e-05,
"loss": 3.4215,
"step": 1820160
},
{
"epoch": 1.02,
"learning_rate": 2.019308316566898e-05,
"loss": 3.437,
"step": 1820672
},
{
"epoch": 1.02,
"learning_rate": 2.018469721815846e-05,
"loss": 3.4247,
"step": 1821184
},
{
"epoch": 1.02,
"learning_rate": 2.017631127064794e-05,
"loss": 3.4439,
"step": 1821696
},
{
"epoch": 1.02,
"learning_rate": 2.016792532313742e-05,
"loss": 3.4382,
"step": 1822208
},
{
"epoch": 1.02,
"learning_rate": 2.0159555754430633e-05,
"loss": 3.446,
"step": 1822720
},
{
"epoch": 1.02,
"learning_rate": 2.0151169806920113e-05,
"loss": 3.4232,
"step": 1823232
},
{
"epoch": 1.02,
"learning_rate": 2.0142783859409593e-05,
"loss": 3.4446,
"step": 1823744
},
{
"epoch": 1.02,
"learning_rate": 2.0134397911899073e-05,
"loss": 3.4364,
"step": 1824256
},
{
"epoch": 1.02,
"learning_rate": 2.012602834319228e-05,
"loss": 3.4427,
"step": 1824768
},
{
"epoch": 1.02,
"learning_rate": 2.011764239568176e-05,
"loss": 3.4288,
"step": 1825280
},
{
"epoch": 1.02,
"learning_rate": 2.010925644817124e-05,
"loss": 3.4349,
"step": 1825792
},
{
"epoch": 1.02,
"learning_rate": 2.010087050066072e-05,
"loss": 3.4391,
"step": 1826304
},
{
"epoch": 1.02,
"learning_rate": 2.0092500931953934e-05,
"loss": 3.4574,
"step": 1826816
},
{
"epoch": 1.02,
"learning_rate": 2.0084114984443414e-05,
"loss": 3.4333,
"step": 1827328
},
{
"epoch": 1.02,
"learning_rate": 2.0075729036932894e-05,
"loss": 3.4377,
"step": 1827840
},
{
"epoch": 1.02,
"learning_rate": 2.006734308942237e-05,
"loss": 3.4436,
"step": 1828352
},
{
"epoch": 1.02,
"learning_rate": 2.0058973520715586e-05,
"loss": 3.431,
"step": 1828864
},
{
"epoch": 1.02,
"learning_rate": 2.0050587573205066e-05,
"loss": 3.4321,
"step": 1829376
},
{
"epoch": 1.02,
"learning_rate": 2.0042201625694546e-05,
"loss": 3.4404,
"step": 1829888
},
{
"epoch": 1.02,
"learning_rate": 2.0033815678184023e-05,
"loss": 3.4411,
"step": 1830400
},
{
"epoch": 1.02,
"learning_rate": 2.0025446109477235e-05,
"loss": 3.4307,
"step": 1830912
},
{
"epoch": 1.02,
"learning_rate": 2.0017060161966715e-05,
"loss": 3.4351,
"step": 1831424
},
{
"epoch": 1.03,
"eval_loss": 3.8580942153930664,
"eval_runtime": 308.9972,
"eval_samples_per_second": 1234.933,
"eval_steps_per_second": 38.593,
"step": 1831680
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2715467226646446e+18,
"trial_name": null,
"trial_params": null
}