abhinavp's picture
Training in progress, epoch 1, checkpoint
6eb4036 verified
{
"best_metric": 3.910466432571411,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/transformer/0/checkpoints/checkpoint-305280",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 305280,
"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
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.1192445377744077e+17,
"trial_name": null,
"trial_params": null
}