abhinavp's picture
Training in progress, epoch 1, checkpoint
38fc914 verified
{
"best_metric": 3.8433103561401367,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/2/checkpoints/checkpoint-915840",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 915840,
"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": 11.016,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8135,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1935,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.989,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8212,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7126,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6089,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5426,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4525,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.408,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.357,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3155,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2618,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2164,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1741,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1411,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1112,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0959,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0536,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0335,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0219,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9772,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9516,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9374,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9288,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8946,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782030879941405e-05,
"loss": 4.8738,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773644932430885e-05,
"loss": 4.8655,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765258984920364e-05,
"loss": 4.8441,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8186,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8018,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7983,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7853,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7813,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7579,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7416,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7452,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7076,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7035,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6897,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6887,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6667,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6773,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6477,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6527,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6424,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6343,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6304,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6062,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5929,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6059,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5919,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.574,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5635,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5697,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5521,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5653,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5385,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5381,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5403,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5218,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.505,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5098,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4938,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4941,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5034,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4972,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4825,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 4.471,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4648,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4748,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4702,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4627,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4621,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4649,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4566,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4309,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4426,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4366,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4238,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.435,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.424,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4328,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.421,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3936,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.405,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4037,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.4055,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3969,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.39,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3905,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3802,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3719,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3742,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.371,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3809,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3577,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3551,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3533,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3604,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3592,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.344,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3449,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3266,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3403,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3264,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3239,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3297,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3276,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3201,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3192,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.31,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3188,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3059,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3059,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3119,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3078,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3053,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.297,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.3023,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2978,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2825,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.3009,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2869,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2934,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.275,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2702,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2688,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2702,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2636,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2789,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2755,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2598,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2641,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2669,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2629,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2667,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2648,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2509,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2567,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.252,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2433,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2538,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2426,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2303,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2548,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2328,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2315,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2346,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2284,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.198453903198242,
"eval_runtime": 303.027,
"eval_samples_per_second": 1259.264,
"eval_steps_per_second": 39.353,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874259923753393e-05,
"loss": 4.2117,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.2218,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2385,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2172,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870907182629558e-05,
"loss": 4.2315,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.2041,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.2185,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.2012,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675560793860965e-05,
"loss": 4.2125,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667174846350445e-05,
"loss": 4.2101,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658788898839925e-05,
"loss": 4.2129,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650402951329405e-05,
"loss": 4.2092,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1947,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1867,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1886,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1906,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608489592580534e-05,
"loss": 4.2008,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8600103645070014e-05,
"loss": 4.1851,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591717697559493e-05,
"loss": 4.1933,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858333175004898e-05,
"loss": 4.2079,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857496218134219e-05,
"loss": 4.1831,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856657623383167e-05,
"loss": 4.1781,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855819028632115e-05,
"loss": 4.1814,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854980433881063e-05,
"loss": 4.1889,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854143477010384e-05,
"loss": 4.1717,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853304882259332e-05,
"loss": 4.175,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.85246628750828e-05,
"loss": 4.1748,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851627692757228e-05,
"loss": 4.1707,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850790735886549e-05,
"loss": 4.1557,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849952141135497e-05,
"loss": 4.161,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849113546384445e-05,
"loss": 4.1598,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482749516333934e-05,
"loss": 4.17,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847437994762714e-05,
"loss": 4.1745,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846599400011662e-05,
"loss": 4.1584,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.84576080526061e-05,
"loss": 4.154,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844922210509558e-05,
"loss": 4.1671,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844085253638879e-05,
"loss": 4.1422,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843246658887827e-05,
"loss": 4.1501,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842408064136775e-05,
"loss": 4.1418,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415694693857225e-05,
"loss": 4.148,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840732512515044e-05,
"loss": 4.1397,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839893917763992e-05,
"loss": 4.1563,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.83905532301294e-05,
"loss": 4.143,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838216728261888e-05,
"loss": 4.1412,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737977139121e-05,
"loss": 4.1408,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836541176640158e-05,
"loss": 4.1442,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8357025818891057e-05,
"loss": 4.1371,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834863987138053e-05,
"loss": 4.1277,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340270302673746e-05,
"loss": 4.1198,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331884355163226e-05,
"loss": 4.1429,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.83234984076527e-05,
"loss": 4.1316,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831511246014218e-05,
"loss": 4.1192,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306742891435395e-05,
"loss": 4.1205,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298356943924875e-05,
"loss": 4.1282,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289970996414354e-05,
"loss": 4.1148,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281585048903834e-05,
"loss": 4.1332,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827321548019705e-05,
"loss": 4.1158,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826482953268653e-05,
"loss": 4.1182,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256443585176003e-05,
"loss": 4.1291,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248057637665483e-05,
"loss": 4.1052,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.82396880689587e-05,
"loss": 4.1042,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823130212144817e-05,
"loss": 4.1127,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822291617393765e-05,
"loss": 4.0963,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821453022642713e-05,
"loss": 4.1005,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820616065772035e-05,
"loss": 4.1137,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819777471020983e-05,
"loss": 4.1182,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818938876269931e-05,
"loss": 4.1043,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818100281518879e-05,
"loss": 4.0986,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817264962528573e-05,
"loss": 4.0891,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816426367777521e-05,
"loss": 4.1087,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815587773026469e-05,
"loss": 4.1055,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814749178275417e-05,
"loss": 4.1048,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139105835243646e-05,
"loss": 4.1056,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130719887733126e-05,
"loss": 4.1076,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812235031902634e-05,
"loss": 4.1069,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811396437151582e-05,
"loss": 4.0849,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.81055784240053e-05,
"loss": 4.0975,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809719247649478e-05,
"loss": 4.0992,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808880652898426e-05,
"loss": 4.0835,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808042058147374e-05,
"loss": 4.1053,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807205101276695e-05,
"loss": 4.0973,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806366506525643e-05,
"loss": 4.1022,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805527911774591e-05,
"loss": 4.0972,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804689317023539e-05,
"loss": 4.0753,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803850722272487e-05,
"loss": 4.0879,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803012127521435e-05,
"loss": 4.087,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802173532770383e-05,
"loss": 4.091,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801334938019331e-05,
"loss": 4.0865,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800497981148652e-05,
"loss": 4.0781,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996593863976e-05,
"loss": 4.0868,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988207916465486e-05,
"loss": 4.0824,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979821968954966e-05,
"loss": 4.0668,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971436021444446e-05,
"loss": 4.0761,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963050073933926e-05,
"loss": 4.0812,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954680505227135e-05,
"loss": 4.0876,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946294557716615e-05,
"loss": 4.0705,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937908610206095e-05,
"loss": 4.0605,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929522662695575e-05,
"loss": 4.0688,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921153093988784e-05,
"loss": 4.0757,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912767146478264e-05,
"loss": 4.0754,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904381198967744e-05,
"loss": 4.0679,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895995251457224e-05,
"loss": 4.0637,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887609303946704e-05,
"loss": 4.0532,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879223356436184e-05,
"loss": 4.067,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708537877294e-05,
"loss": 4.0539,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786246784021888e-05,
"loss": 4.0584,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785408189270836e-05,
"loss": 4.063,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784569594519783e-05,
"loss": 4.0623,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783730999768731e-05,
"loss": 4.0563,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0602,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.0509,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781216853395948e-05,
"loss": 4.057,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780378258644896e-05,
"loss": 4.0504,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779539663893844e-05,
"loss": 4.0485,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778701069142792e-05,
"loss": 4.0614,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.77786247439174e-05,
"loss": 4.0609,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777025517521062e-05,
"loss": 4.0558,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.77618692277001e-05,
"loss": 4.0505,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775348328018958e-05,
"loss": 4.0545,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.0531,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.0391,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0586,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.0459,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711569921440707e-05,
"loss": 4.0534,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703183973930186e-05,
"loss": 4.0375,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694814405223396e-05,
"loss": 4.0379,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686428457712876e-05,
"loss": 4.0351,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.7678042510202355e-05,
"loss": 4.0353,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766965656269184e-05,
"loss": 4.0345,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766128699398505e-05,
"loss": 4.0466,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765290104647453e-05,
"loss": 4.0516,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764451509896401e-05,
"loss": 4.0379,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.0318,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0423,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761937363523618e-05,
"loss": 4.0417,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761098768772566e-05,
"loss": 4.0467,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760260174021514e-05,
"loss": 4.0402,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759421579270462e-05,
"loss": 4.0369,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.0288,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0403,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569074328976796e-05,
"loss": 4.0298,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560688381466276e-05,
"loss": 4.0334,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552302433955756e-05,
"loss": 4.0316,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543916486445236e-05,
"loss": 4.0212,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535546917738445e-05,
"loss": 4.0453,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527160970227925e-05,
"loss": 4.0253,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518775022717405e-05,
"loss": 4.0204,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510389075206885e-05,
"loss": 4.0248,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502019506500094e-05,
"loss": 4.0216,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.029199600219727,
"eval_runtime": 302.4487,
"eval_samples_per_second": 1261.672,
"eval_steps_per_second": 39.428,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493633558989574e-05,
"loss": 4.0063,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485247611479054e-05,
"loss": 4.0207,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476861663968534e-05,
"loss": 4.0335,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468475716458014e-05,
"loss": 4.0191,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460089768947494e-05,
"loss": 4.0317,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451703821436974e-05,
"loss": 4.0104,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443317873926453e-05,
"loss": 4.024,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434931926415933e-05,
"loss": 4.0021,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742656235770914e-05,
"loss": 4.0198,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741817641019862e-05,
"loss": 4.0171,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.74097904626881e-05,
"loss": 4.0152,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740140451517758e-05,
"loss": 4.0237,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.0022,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 3.9996,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 3.9997,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 4.0053,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 4.0129,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 4.0019,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734273564021141e-05,
"loss": 4.0069,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733434969270089e-05,
"loss": 4.0264,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732596374519037e-05,
"loss": 4.0011,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731757779767985e-05,
"loss": 3.9965,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309208228973056e-05,
"loss": 4.0035,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300822281462536e-05,
"loss": 4.0099,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292436333952016e-05,
"loss": 3.9942,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7284050386441496e-05,
"loss": 3.9982,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275664438930976e-05,
"loss": 3.9999,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267294870224185e-05,
"loss": 3.9967,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258908922713665e-05,
"loss": 3.9824,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725052297520315e-05,
"loss": 3.9906,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724213702769263e-05,
"loss": 3.9926,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723376745898584e-05,
"loss": 3.9961,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722538151147532e-05,
"loss": 4.0089,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.72169955639648e-05,
"loss": 3.9873,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720860961645428e-05,
"loss": 3.9865,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720022366894376e-05,
"loss": 3.9971,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719185410023697e-05,
"loss": 3.9808,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718346815272645e-05,
"loss": 3.9815,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717508220521593e-05,
"loss": 3.9754,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716669625770541e-05,
"loss": 3.9873,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715831031019489e-05,
"loss": 3.9742,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149940741488105e-05,
"loss": 3.9963,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141554793977585e-05,
"loss": 3.9778,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133168846467065e-05,
"loss": 3.9862,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124782898956545e-05,
"loss": 3.985,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116396951446025e-05,
"loss": 3.9793,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108027382739234e-05,
"loss": 3.9812,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099641435228714e-05,
"loss": 3.9677,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091255487718194e-05,
"loss": 3.9628,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082869540207674e-05,
"loss": 3.9863,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707449997150088e-05,
"loss": 3.9779,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706611402399036e-05,
"loss": 3.9669,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705772807647984e-05,
"loss": 3.9704,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704934212896932e-05,
"loss": 3.9775,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704097256026254e-05,
"loss": 3.957,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703258661275202e-05,
"loss": 3.9793,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.70242006652415e-05,
"loss": 3.9672,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701581471773098e-05,
"loss": 3.9656,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700744514902419e-05,
"loss": 3.9827,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699905920151367e-05,
"loss": 3.9603,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699067325400315e-05,
"loss": 3.9572,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698228730649263e-05,
"loss": 3.9676,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.69739013589821e-05,
"loss": 3.9519,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696553179027532e-05,
"loss": 3.9552,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69571458427648e-05,
"loss": 3.969,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694875989525428e-05,
"loss": 3.9715,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694037394774376e-05,
"loss": 3.9568,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693198800023324e-05,
"loss": 3.9577,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692361843152645e-05,
"loss": 3.9451,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915232484015926e-05,
"loss": 3.9646,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906846536505406e-05,
"loss": 3.9609,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898460588994886e-05,
"loss": 3.9657,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890091020288095e-05,
"loss": 3.9628,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881705072777575e-05,
"loss": 3.9668,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873319125267055e-05,
"loss": 3.9724,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864933177756535e-05,
"loss": 3.9456,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685656360904975e-05,
"loss": 3.9581,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684817766153923e-05,
"loss": 3.9628,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683979171402871e-05,
"loss": 3.9459,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683140576651819e-05,
"loss": 3.9665,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682301981900767e-05,
"loss": 3.9611,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681465025030088e-05,
"loss": 3.9673,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680626430279036e-05,
"loss": 3.9621,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679787835527984e-05,
"loss": 3.941,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678949240776932e-05,
"loss": 3.9536,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678112283906253e-05,
"loss": 3.9507,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677273689155201e-05,
"loss": 3.9602,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676435094404149e-05,
"loss": 3.95,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675596499653097e-05,
"loss": 3.9497,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747595427824184e-05,
"loss": 3.9538,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739209480313664e-05,
"loss": 3.9515,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730823532803144e-05,
"loss": 3.9367,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722437585292624e-05,
"loss": 3.9433,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714051637782104e-05,
"loss": 3.9533,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670568206907531e-05,
"loss": 3.9585,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669729612156479e-05,
"loss": 3.9472,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668891017405427e-05,
"loss": 3.9302,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668052422654375e-05,
"loss": 3.9418,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667215465783696e-05,
"loss": 3.9488,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666376871032644e-05,
"loss": 3.9468,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665538276281592e-05,
"loss": 3.9437,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.66469968153054e-05,
"loss": 3.9397,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663862724659862e-05,
"loss": 3.927,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66302412990881e-05,
"loss": 3.9476,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662185535157758e-05,
"loss": 3.9244,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661346940406706e-05,
"loss": 3.9383,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660509983536027e-05,
"loss": 3.9329,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659671388784975e-05,
"loss": 3.9467,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658832794033923e-05,
"loss": 3.9278,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579941992828707e-05,
"loss": 3.9417,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571572424121916e-05,
"loss": 3.9311,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563186476611396e-05,
"loss": 3.9308,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554800529100876e-05,
"loss": 3.9355,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546414581590356e-05,
"loss": 3.9271,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653804501288357e-05,
"loss": 3.942,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652965906537305e-05,
"loss": 3.9408,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652127311786253e-05,
"loss": 3.936,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651288717035201e-05,
"loss": 3.9309,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650451760164522e-05,
"loss": 3.9346,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.64961316541347e-05,
"loss": 3.9386,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648774570662418e-05,
"loss": 3.9186,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647935975911366e-05,
"loss": 3.9408,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647099019040687e-05,
"loss": 3.931,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646260424289635e-05,
"loss": 3.9372,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645421829538583e-05,
"loss": 3.9248,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644583234787531e-05,
"loss": 3.927,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643744640036479e-05,
"loss": 3.9156,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429076831658005e-05,
"loss": 3.923,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420690884147485e-05,
"loss": 3.9197,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412304936636965e-05,
"loss": 3.9328,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403918989126445e-05,
"loss": 3.9383,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395549420419654e-05,
"loss": 3.9264,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387163472909134e-05,
"loss": 3.9191,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378777525398614e-05,
"loss": 3.9265,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370391577888094e-05,
"loss": 3.9291,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.63620220091813e-05,
"loss": 3.934,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635363606167078e-05,
"loss": 3.9263,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634525011416026e-05,
"loss": 3.9212,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633686416664974e-05,
"loss": 3.9261,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632849459794296e-05,
"loss": 3.9309,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632010865043244e-05,
"loss": 3.9169,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631172270292192e-05,
"loss": 3.9246,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.63033367554114e-05,
"loss": 3.9203,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629496718670461e-05,
"loss": 3.9127,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628658123919409e-05,
"loss": 3.9349,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627819529168357e-05,
"loss": 3.9181,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626980934417305e-05,
"loss": 3.913,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626142339666253e-05,
"loss": 3.9176,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6253053827955737e-05,
"loss": 3.9117,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9546828269958496,
"eval_runtime": 303.1541,
"eval_samples_per_second": 1258.736,
"eval_steps_per_second": 39.336,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244667880445217e-05,
"loss": 3.9057,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236281932934697e-05,
"loss": 3.9127,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227895985424176e-05,
"loss": 3.9289,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621952641671739e-05,
"loss": 3.9132,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621114046920687e-05,
"loss": 3.9329,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620275452169635e-05,
"loss": 3.9018,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194368574185825e-05,
"loss": 3.9203,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185982626675305e-05,
"loss": 3.8985,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617761305796852e-05,
"loss": 3.9157,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6169227110458e-05,
"loss": 3.9158,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160841162947474e-05,
"loss": 3.9105,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152455215436954e-05,
"loss": 3.9187,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614408564673017e-05,
"loss": 3.8988,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613569969921965e-05,
"loss": 3.8987,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612731375170913e-05,
"loss": 3.8969,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611892780419861e-05,
"loss": 3.9014,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611054185668809e-05,
"loss": 3.9105,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610215590917757e-05,
"loss": 3.9028,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609376996166705e-05,
"loss": 3.9073,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608538401415653e-05,
"loss": 3.9235,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607701444544974e-05,
"loss": 3.9055,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606862849793922e-05,
"loss": 3.9023,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.60602425504287e-05,
"loss": 3.904,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605185660291818e-05,
"loss": 3.91,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604348703421139e-05,
"loss": 3.893,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035101086700875e-05,
"loss": 3.902,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026715139190355e-05,
"loss": 3.9037,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018329191679835e-05,
"loss": 3.8954,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009959622973044e-05,
"loss": 3.889,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001573675462524e-05,
"loss": 3.8893,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5993187727952004e-05,
"loss": 3.9009,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984801780441484e-05,
"loss": 3.8986,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597643221173469e-05,
"loss": 3.9121,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596804626422417e-05,
"loss": 3.8981,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595966031671365e-05,
"loss": 3.8846,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595127436920313e-05,
"loss": 3.8999,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594290480049634e-05,
"loss": 3.8914,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593451885298583e-05,
"loss": 3.8843,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592613290547531e-05,
"loss": 3.8856,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591774695796479e-05,
"loss": 3.8902,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909377389258e-05,
"loss": 3.8835,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590099144174748e-05,
"loss": 3.9023,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589260549423696e-05,
"loss": 3.8859,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588421954672644e-05,
"loss": 3.8918,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875849978019646e-05,
"loss": 3.8945,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867464030509126e-05,
"loss": 3.8849,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5859078082998606e-05,
"loss": 3.8908,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850692135488086e-05,
"loss": 3.8755,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842322566781295e-05,
"loss": 3.8643,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833936619270775e-05,
"loss": 3.898,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582555067176026e-05,
"loss": 3.8861,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581716472424974e-05,
"loss": 3.8805,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580879515554295e-05,
"loss": 3.877,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580040920803243e-05,
"loss": 3.884,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579202326052191e-05,
"loss": 3.8688,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578363731301139e-05,
"loss": 3.8884,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.57752677443046e-05,
"loss": 3.881,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576688179679408e-05,
"loss": 3.8777,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575849584928356e-05,
"loss": 3.8906,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.575010990177304e-05,
"loss": 3.8707,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574174033306625e-05,
"loss": 3.869,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573335438555573e-05,
"loss": 3.8837,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724968438045216e-05,
"loss": 3.8588,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716582490534696e-05,
"loss": 3.8641,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708212921827905e-05,
"loss": 3.8838,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699826974317385e-05,
"loss": 3.884,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691441026806865e-05,
"loss": 3.8662,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5683055079296345e-05,
"loss": 3.8773,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674685510589554e-05,
"loss": 3.857,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666299563079034e-05,
"loss": 3.879,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657913615568514e-05,
"loss": 3.8749,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649527668057994e-05,
"loss": 3.8801,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.56411580993512e-05,
"loss": 3.875,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563277215184068e-05,
"loss": 3.8803,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562438620433017e-05,
"loss": 3.8885,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561600025681965e-05,
"loss": 3.8592,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560763068811286e-05,
"loss": 3.8761,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559924474060234e-05,
"loss": 3.8797,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559085879309182e-05,
"loss": 3.8575,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.55824728455813e-05,
"loss": 3.887,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557410327687451e-05,
"loss": 3.877,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556571732936399e-05,
"loss": 3.8788,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555733138185347e-05,
"loss": 3.8822,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554894543434295e-05,
"loss": 3.8601,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554055948683243e-05,
"loss": 3.8638,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.5532189918125636e-05,
"loss": 3.8699,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552380397061512e-05,
"loss": 3.8769,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.55154180231046e-05,
"loss": 3.8662,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550703207559408e-05,
"loss": 3.8679,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549866250688729e-05,
"loss": 3.8668,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549027655937677e-05,
"loss": 3.8768,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548189061186625e-05,
"loss": 3.8563,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473504664355725e-05,
"loss": 3.8633,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546513509564894e-05,
"loss": 3.8713,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545674914813842e-05,
"loss": 3.8786,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.54483632006279e-05,
"loss": 3.8665,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439977253117374e-05,
"loss": 3.8509,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543160768441059e-05,
"loss": 3.8607,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542322173690008e-05,
"loss": 3.8662,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541483578938956e-05,
"loss": 3.8678,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540644984187903e-05,
"loss": 3.8661,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5398080273172246e-05,
"loss": 3.8606,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389694325661726e-05,
"loss": 3.848,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.53813083781512e-05,
"loss": 3.8649,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537292243064068e-05,
"loss": 3.848,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364552861933895e-05,
"loss": 3.8565,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356166914423375e-05,
"loss": 3.8525,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534778096691285e-05,
"loss": 3.8675,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339411398206064e-05,
"loss": 3.8501,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5331025450695544e-05,
"loss": 3.8674,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532263950318503e-05,
"loss": 3.8485,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314253555674504e-05,
"loss": 3.8565,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305867608163983e-05,
"loss": 3.8565,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297481660653463e-05,
"loss": 3.8534,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528909571314294e-05,
"loss": 3.8593,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528070976563242e-05,
"loss": 3.8683,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527234019692563e-05,
"loss": 3.8601,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526395424941511e-05,
"loss": 3.8533,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525556830190459e-05,
"loss": 3.8572,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524718235439407e-05,
"loss": 3.861,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523881278568728e-05,
"loss": 3.8431,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523042683817677e-05,
"loss": 3.8638,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522204089066625e-05,
"loss": 3.8506,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521365494315573e-05,
"loss": 3.8629,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520528537444894e-05,
"loss": 3.8514,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519689942693842e-05,
"loss": 3.8536,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.51885134794279e-05,
"loss": 3.8379,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.518012753191738e-05,
"loss": 3.851,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171757963210586e-05,
"loss": 3.8447,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163372015700066e-05,
"loss": 3.8544,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154986068189546e-05,
"loss": 3.8599,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146600120679026e-05,
"loss": 3.8554,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5138230551972235e-05,
"loss": 3.8417,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512984460446172e-05,
"loss": 3.8544,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.51214586569512e-05,
"loss": 3.8577,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511307270944068e-05,
"loss": 3.8575,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510470314073389e-05,
"loss": 3.8542,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509631719322337e-05,
"loss": 3.8479,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508793124571285e-05,
"loss": 3.8498,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507954529820233e-05,
"loss": 3.8595,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507117572949554e-05,
"loss": 3.8426,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506278978198502e-05,
"loss": 3.854,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.50544038344745e-05,
"loss": 3.8428,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504601788696398e-05,
"loss": 3.8457,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503764831825719e-05,
"loss": 3.8611,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5029262370746675e-05,
"loss": 3.8473,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020876423236155e-05,
"loss": 3.8405,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012490475725635e-05,
"loss": 3.84,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5004120907018844e-05,
"loss": 3.846,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9137043952941895,
"eval_runtime": 304.2318,
"eval_samples_per_second": 1254.277,
"eval_steps_per_second": 39.197,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995734959508324e-05,
"loss": 3.8285,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987349011997804e-05,
"loss": 3.8423,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978963064487284e-05,
"loss": 3.8529,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970577116976764e-05,
"loss": 3.8442,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962191169466244e-05,
"loss": 3.8582,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953805221955724e-05,
"loss": 3.8393,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945419274445204e-05,
"loss": 3.8436,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4937033326934684e-05,
"loss": 3.8334,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492866375822789e-05,
"loss": 3.8398,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492027781071737e-05,
"loss": 3.8432,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491189186320685e-05,
"loss": 3.8423,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490350591569633e-05,
"loss": 3.8499,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489515272579328e-05,
"loss": 3.8273,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488676677828276e-05,
"loss": 3.8329,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487838083077224e-05,
"loss": 3.8302,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486999488326172e-05,
"loss": 3.8316,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.48616089357512e-05,
"loss": 3.8413,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485322298824068e-05,
"loss": 3.8332,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484483704073016e-05,
"loss": 3.8394,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483645109321963e-05,
"loss": 3.8551,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482808152451285e-05,
"loss": 3.8381,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481969557700233e-05,
"loss": 3.8346,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481130962949181e-05,
"loss": 3.8352,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480292368198129e-05,
"loss": 3.8392,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.47945541132745e-05,
"loss": 3.824,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478616816576398e-05,
"loss": 3.8368,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777782218253456e-05,
"loss": 3.8323,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.4769396270742936e-05,
"loss": 3.8302,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476102670203615e-05,
"loss": 3.8222,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475264075452563e-05,
"loss": 3.823,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4744254807015105e-05,
"loss": 3.8298,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.4735868859504585e-05,
"loss": 3.8333,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.47274992907978e-05,
"loss": 3.8439,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471911334328728e-05,
"loss": 3.831,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471072739577676e-05,
"loss": 3.8194,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470234144826624e-05,
"loss": 3.8343,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693971879559456e-05,
"loss": 3.8318,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468558593204893e-05,
"loss": 3.8156,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467719998453841e-05,
"loss": 3.8173,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466881403702789e-05,
"loss": 3.826,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660444468321105e-05,
"loss": 3.8162,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465205852081058e-05,
"loss": 3.8381,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464367257330006e-05,
"loss": 3.8217,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463528662578954e-05,
"loss": 3.8248,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626917057082754e-05,
"loss": 3.8294,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618531109572234e-05,
"loss": 3.8257,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610145162061714e-05,
"loss": 3.8243,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601759214551194e-05,
"loss": 3.8113,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.45933896458444e-05,
"loss": 3.7982,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458500369833388e-05,
"loss": 3.8394,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457661775082336e-05,
"loss": 3.8181,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456823180331284e-05,
"loss": 3.819,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455986223460605e-05,
"loss": 3.817,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455147628709553e-05,
"loss": 3.815,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454309033958501e-05,
"loss": 3.8082,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453470439207449e-05,
"loss": 3.822,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452633482336771e-05,
"loss": 3.8192,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451794887585719e-05,
"loss": 3.8142,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450956292834667e-05,
"loss": 3.834,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450117698083615e-05,
"loss": 3.8048,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449280741212936e-05,
"loss": 3.8023,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448442146461884e-05,
"loss": 3.8256,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447603551710832e-05,
"loss": 3.7929,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.44676495695978e-05,
"loss": 3.8013,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459280000891006e-05,
"loss": 3.823,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450894053380486e-05,
"loss": 3.8236,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442508105869966e-05,
"loss": 3.8069,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.4434122158359446e-05,
"loss": 3.8155,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442575258965266e-05,
"loss": 3.7968,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441736664214214e-05,
"loss": 3.8158,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440898069463162e-05,
"loss": 3.8131,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.44005947471211e-05,
"loss": 3.8166,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439222517841431e-05,
"loss": 3.8114,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438383923090379e-05,
"loss": 3.8186,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437545328339327e-05,
"loss": 3.8253,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436706733588275e-05,
"loss": 3.8027,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435869776717596e-05,
"loss": 3.8108,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435031181966544e-05,
"loss": 3.8196,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434192587215492e-05,
"loss": 3.7979,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.43335399246444e-05,
"loss": 3.8228,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4325170355937615e-05,
"loss": 3.8196,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316784408427095e-05,
"loss": 3.8192,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308398460916575e-05,
"loss": 3.8202,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4300012513406055e-05,
"loss": 3.8026,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291642944699264e-05,
"loss": 3.8011,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283256997188744e-05,
"loss": 3.8087,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274871049678224e-05,
"loss": 3.8198,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266485102167704e-05,
"loss": 3.8086,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425811553346091e-05,
"loss": 3.8067,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424972958595039e-05,
"loss": 3.8047,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424134363843987e-05,
"loss": 3.8183,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423297406973308e-05,
"loss": 3.8,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422458812222257e-05,
"loss": 3.8003,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421620217471205e-05,
"loss": 3.8097,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420781622720153e-05,
"loss": 3.8199,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419943027969101e-05,
"loss": 3.8081,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419104433218049e-05,
"loss": 3.7948,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418265838466997e-05,
"loss": 3.8012,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417427243715945e-05,
"loss": 3.8058,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416590286845266e-05,
"loss": 3.8114,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415751692094214e-05,
"loss": 3.8056,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414913097343162e-05,
"loss": 3.8071,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.41407450259211e-05,
"loss": 3.7905,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413237545721431e-05,
"loss": 3.8032,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412398950970379e-05,
"loss": 3.7907,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115603562193267e-05,
"loss": 3.8039,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107217614682747e-05,
"loss": 3.7871,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409884804597596e-05,
"loss": 3.8154,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409047847726917e-05,
"loss": 3.7932,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408209252975865e-05,
"loss": 3.8031,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407370658224813e-05,
"loss": 3.7953,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406532063473761e-05,
"loss": 3.7975,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405693468722709e-05,
"loss": 3.7995,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404854873971657e-05,
"loss": 3.7995,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404016279220605e-05,
"loss": 3.8025,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403177684469553e-05,
"loss": 3.8098,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402340727598874e-05,
"loss": 3.8025,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401502132847822e-05,
"loss": 3.7999,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.40066353809677e-05,
"loss": 3.8005,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399824943345719e-05,
"loss": 3.8066,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.3989879864750396e-05,
"loss": 3.783,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.3981493917239876e-05,
"loss": 3.8074,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.3973107969729356e-05,
"loss": 3.7932,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396472202221883e-05,
"loss": 3.8078,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956352453512045e-05,
"loss": 3.7935,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947966506001525e-05,
"loss": 3.8008,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939580558491005e-05,
"loss": 3.7853,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393119461098048e-05,
"loss": 3.7926,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922825042273694e-05,
"loss": 3.7941,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914439094763174e-05,
"loss": 3.7973,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3906053147252654e-05,
"loss": 3.8005,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897667199742134e-05,
"loss": 3.8058,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388929763103535e-05,
"loss": 3.7855,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388091168352483e-05,
"loss": 3.7998,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.38725257360143e-05,
"loss": 3.8052,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386413978850378e-05,
"loss": 3.8028,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855770219797e-05,
"loss": 3.7969,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384738427228648e-05,
"loss": 3.7978,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383899832477595e-05,
"loss": 3.792,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383061237726543e-05,
"loss": 3.8069,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382224280855865e-05,
"loss": 3.7872,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381385686104813e-05,
"loss": 3.8001,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380547091353761e-05,
"loss": 3.7912,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379708496602709e-05,
"loss": 3.7902,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.37887153973203e-05,
"loss": 3.8065,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780329449809777e-05,
"loss": 3.7942,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771943502299257e-05,
"loss": 3.7896,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763557554788736e-05,
"loss": 3.7806,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375518798608195e-05,
"loss": 3.7932,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.8878939151763916,
"eval_runtime": 380.5554,
"eval_samples_per_second": 1002.721,
"eval_steps_per_second": 31.336,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746802038571426e-05,
"loss": 3.7835,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3738416091060905e-05,
"loss": 3.7854,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.3730030143550385e-05,
"loss": 3.8016,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.37216605748436e-05,
"loss": 3.7921,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371327462733308e-05,
"loss": 3.8049,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370488867982256e-05,
"loss": 3.7877,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369650273231204e-05,
"loss": 3.7866,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368813316360525e-05,
"loss": 3.7826,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367974721609473e-05,
"loss": 3.7849,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367136126858421e-05,
"loss": 3.7934,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366297532107369e-05,
"loss": 3.7938,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.36546057523669e-05,
"loss": 3.7913,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.3646236183660115e-05,
"loss": 3.7815,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.3637850236149595e-05,
"loss": 3.7779,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362946428863907e-05,
"loss": 3.7783,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3621078341128555e-05,
"loss": 3.7783,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612692393618035e-05,
"loss": 3.7876,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.3604306446107515e-05,
"loss": 3.7836,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.3595920498596995e-05,
"loss": 3.7885,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.3587534551086475e-05,
"loss": 3.802,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3579164982379684e-05,
"loss": 3.7897,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.3570779034869164e-05,
"loss": 3.7774,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.3562393087358644e-05,
"loss": 3.7837,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.3554007139848124e-05,
"loss": 3.7873,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354563757114133e-05,
"loss": 3.7749,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353725162363081e-05,
"loss": 3.7847,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352886567612029e-05,
"loss": 3.7813,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352047972860977e-05,
"loss": 3.7804,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351211015990299e-05,
"loss": 3.7752,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350372421239247e-05,
"loss": 3.7682,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.349533826488195e-05,
"loss": 3.7788,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348695231737143e-05,
"loss": 3.7823,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347858274866464e-05,
"loss": 3.7909,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.347019680115412e-05,
"loss": 3.7822,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.34618108536436e-05,
"loss": 3.7674,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345342490613308e-05,
"loss": 3.7863,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.3445055337426287e-05,
"loss": 3.7815,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.3436669389915766e-05,
"loss": 3.7622,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.3428283442405246e-05,
"loss": 3.773,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.3419897494894726e-05,
"loss": 3.7743,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341152792618794e-05,
"loss": 3.7695,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340314197867742e-05,
"loss": 3.7856,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.33947560311669e-05,
"loss": 3.7752,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338637008365638e-05,
"loss": 3.774,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337800051494959e-05,
"loss": 3.7778,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336961456743907e-05,
"loss": 3.7756,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336122861992855e-05,
"loss": 3.7812,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335284267241803e-05,
"loss": 3.76,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334447310371124e-05,
"loss": 3.7448,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333608715620072e-05,
"loss": 3.7919,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.33277012086902e-05,
"loss": 3.771,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.3319331639983416e-05,
"loss": 3.7767,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.3310945692472896e-05,
"loss": 3.7662,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.3302559744962376e-05,
"loss": 3.7654,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.3294173797451856e-05,
"loss": 3.7627,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.3285804228745065e-05,
"loss": 3.7681,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.3277418281234545e-05,
"loss": 3.7742,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.3269032333724025e-05,
"loss": 3.7618,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.3260646386213505e-05,
"loss": 3.7859,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.3252276817506714e-05,
"loss": 3.7621,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.3243890869996194e-05,
"loss": 3.7525,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.3235504922485674e-05,
"loss": 3.7771,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.3227118974975154e-05,
"loss": 3.7489,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321874940626836e-05,
"loss": 3.7512,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321036345875785e-05,
"loss": 3.7747,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320197751124733e-05,
"loss": 3.7726,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319359156373681e-05,
"loss": 3.7605,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318522199503002e-05,
"loss": 3.7682,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.31768360475195e-05,
"loss": 3.748,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316845010000898e-05,
"loss": 3.7702,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.316006415249846e-05,
"loss": 3.7621,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315169458379167e-05,
"loss": 3.7732,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314330863628115e-05,
"loss": 3.7645,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313492268877063e-05,
"loss": 3.7691,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312653674126011e-05,
"loss": 3.7793,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.3118167172553317e-05,
"loss": 3.7534,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.31097812250428e-05,
"loss": 3.7666,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310139527753228e-05,
"loss": 3.7706,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309300933002176e-05,
"loss": 3.753,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308463976131497e-05,
"loss": 3.7754,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307625381380445e-05,
"loss": 3.7755,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306786786629393e-05,
"loss": 3.7695,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305948191878341e-05,
"loss": 3.7803,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305111235007662e-05,
"loss": 3.7542,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.30427264025661e-05,
"loss": 3.7531,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303434045505558e-05,
"loss": 3.7625,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.302595450754506e-05,
"loss": 3.7688,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301758493883827e-05,
"loss": 3.7688,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300919899132776e-05,
"loss": 3.7589,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300081304381724e-05,
"loss": 3.7578,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299242709630672e-05,
"loss": 3.7716,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2984057527599926e-05,
"loss": 3.7548,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.2975671580089406e-05,
"loss": 3.7564,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.2967285632578886e-05,
"loss": 3.7622,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.2958899685068366e-05,
"loss": 3.774,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.2950530116361575e-05,
"loss": 3.7657,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.2942144168851055e-05,
"loss": 3.7472,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.2933758221340535e-05,
"loss": 3.7548,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.2925372273830015e-05,
"loss": 3.7618,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.2917002705123224e-05,
"loss": 3.7638,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290861675761271e-05,
"loss": 3.7617,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.290023081010219e-05,
"loss": 3.7612,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289184486259167e-05,
"loss": 3.7449,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288347529388488e-05,
"loss": 3.7542,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287508934637436e-05,
"loss": 3.7527,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286670339886384e-05,
"loss": 3.7576,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285831745135332e-05,
"loss": 3.7417,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284994788264653e-05,
"loss": 3.7722,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284157831393974e-05,
"loss": 3.7493,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.283319236642922e-05,
"loss": 3.7574,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.28248064189187e-05,
"loss": 3.7464,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281642047140818e-05,
"loss": 3.7582,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2808034523897664e-05,
"loss": 3.7547,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.2799648576387144e-05,
"loss": 3.7501,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2791262628876624e-05,
"loss": 3.7583,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.27828766813661e-05,
"loss": 3.769,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277450711265931e-05,
"loss": 3.7518,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276612116514879e-05,
"loss": 3.7647,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275773521763827e-05,
"loss": 3.7512,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.2749349270127746e-05,
"loss": 3.7618,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274097970142096e-05,
"loss": 3.7431,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273259375391044e-05,
"loss": 3.7615,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272420780639992e-05,
"loss": 3.7476,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.27158218588894e-05,
"loss": 3.7618,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270745229018262e-05,
"loss": 3.7543,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.26990663426721e-05,
"loss": 3.7549,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269068039516157e-05,
"loss": 3.7397,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268229444765105e-05,
"loss": 3.7493,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267392487894427e-05,
"loss": 3.7494,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266553893143375e-05,
"loss": 3.7564,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.265715298392322e-05,
"loss": 3.7501,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.26487670364127e-05,
"loss": 3.7621,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2640397467705916e-05,
"loss": 3.7452,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2632011520195396e-05,
"loss": 3.756,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262362557268487e-05,
"loss": 3.7587,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2615239625174356e-05,
"loss": 3.7613,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260687005646757e-05,
"loss": 3.7522,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2598484108957045e-05,
"loss": 3.7545,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2590098161446525e-05,
"loss": 3.7471,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.2581712213936005e-05,
"loss": 3.767,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257334264522922e-05,
"loss": 3.7421,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.2564956697718694e-05,
"loss": 3.7578,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.2556570750208174e-05,
"loss": 3.7464,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.2548184802697654e-05,
"loss": 3.7503,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253981523399087e-05,
"loss": 3.7592,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253142928648034e-05,
"loss": 3.7487,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252304333896982e-05,
"loss": 3.7527,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251465739145931e-05,
"loss": 3.7343,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250627144394879e-05,
"loss": 3.7526,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.87255859375,
"eval_runtime": 378.9148,
"eval_samples_per_second": 1007.063,
"eval_steps_per_second": 31.471,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249788549643827e-05,
"loss": 3.7402,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248949954892775e-05,
"loss": 3.7409,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248111360141723e-05,
"loss": 3.7576,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247272765390671e-05,
"loss": 3.7526,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246434170639619e-05,
"loss": 3.7598,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245595575888567e-05,
"loss": 3.7448,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244756981137515e-05,
"loss": 3.7449,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243918386386463e-05,
"loss": 3.7417,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243081429515784e-05,
"loss": 3.7453,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242242834764732e-05,
"loss": 3.7513,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.24140424001368e-05,
"loss": 3.747,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240565645262628e-05,
"loss": 3.7477,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239730326272322e-05,
"loss": 3.7397,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.23889173152127e-05,
"loss": 3.7372,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238053136770218e-05,
"loss": 3.7388,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237214542019166e-05,
"loss": 3.7325,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236375947268114e-05,
"loss": 3.7467,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235537352517062e-05,
"loss": 3.7429,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.23469875776601e-05,
"loss": 3.7441,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233860163014958e-05,
"loss": 3.7582,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.233023206144279e-05,
"loss": 3.7553,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232184611393227e-05,
"loss": 3.7394,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231346016642175e-05,
"loss": 3.739,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.2305074218911225e-05,
"loss": 3.7456,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.229670465020444e-05,
"loss": 3.7391,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.228831870269393e-05,
"loss": 3.7408,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.227993275518341e-05,
"loss": 3.7432,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227154680767288e-05,
"loss": 3.7409,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2263177238966096e-05,
"loss": 3.7334,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254791291455576e-05,
"loss": 3.7295,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2246405343945056e-05,
"loss": 3.7313,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223801939643453e-05,
"loss": 3.7411,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.2229649827727745e-05,
"loss": 3.7498,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.2221263880217225e-05,
"loss": 3.7462,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.22128779327067e-05,
"loss": 3.7283,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220449198519618e-05,
"loss": 3.7412,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.2196122416489394e-05,
"loss": 3.7426,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218773646897888e-05,
"loss": 3.7248,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.2179350521468354e-05,
"loss": 3.7338,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.2170964573957834e-05,
"loss": 3.7332,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216259500525105e-05,
"loss": 3.7263,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215420905774053e-05,
"loss": 3.7444,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214582311023e-05,
"loss": 3.734,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213745354152322e-05,
"loss": 3.7381,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.21290675940127e-05,
"loss": 3.7362,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212068164650217e-05,
"loss": 3.7342,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211229569899165e-05,
"loss": 3.7406,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.210392613028487e-05,
"loss": 3.7245,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209554018277435e-05,
"loss": 3.702,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208715423526383e-05,
"loss": 3.7493,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207876828775331e-05,
"loss": 3.7304,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070398719046524e-05,
"loss": 3.7372,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2062012771536004e-05,
"loss": 3.7292,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.205362682402548e-05,
"loss": 3.7267,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204524087651496e-05,
"loss": 3.72,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203687130780817e-05,
"loss": 3.7313,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.2028485360297646e-05,
"loss": 3.736,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.2020099412787126e-05,
"loss": 3.7216,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.2011713465276606e-05,
"loss": 3.7446,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200334389656982e-05,
"loss": 3.7269,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.19949579490593e-05,
"loss": 3.715,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198657200154878e-05,
"loss": 3.7336,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197818605403826e-05,
"loss": 3.7164,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196981648533148e-05,
"loss": 3.7096,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196143053782095e-05,
"loss": 3.7383,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195304459031043e-05,
"loss": 3.7342,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194465864279991e-05,
"loss": 3.7226,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193628907409312e-05,
"loss": 3.7265,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.19279031265826e-05,
"loss": 3.7126,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191951717907208e-05,
"loss": 3.7298,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191113123156156e-05,
"loss": 3.7272,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902761662854775e-05,
"loss": 3.7294,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1894375715344255e-05,
"loss": 3.7279,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885989767833735e-05,
"loss": 3.7297,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1877603820323215e-05,
"loss": 3.7415,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1869234251616424e-05,
"loss": 3.715,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860848304105904e-05,
"loss": 3.731,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1852462356595384e-05,
"loss": 3.7263,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1844076409084864e-05,
"loss": 3.7162,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183570684037807e-05,
"loss": 3.7362,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182732089286755e-05,
"loss": 3.739,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181893494535703e-05,
"loss": 3.7285,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.181054899784651e-05,
"loss": 3.7424,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180217942913973e-05,
"loss": 3.7155,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179379348162921e-05,
"loss": 3.7151,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178540753411869e-05,
"loss": 3.7241,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.177702158660817e-05,
"loss": 3.7345,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176865201790138e-05,
"loss": 3.7235,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.176026607039086e-05,
"loss": 3.7243,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175188012288034e-05,
"loss": 3.7237,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174349417536982e-05,
"loss": 3.7324,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173512460666303e-05,
"loss": 3.7175,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172673865915251e-05,
"loss": 3.7195,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171835271164199e-05,
"loss": 3.7262,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170996676413147e-05,
"loss": 3.7373,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170159719542468e-05,
"loss": 3.7256,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169321124791416e-05,
"loss": 3.7082,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168482530040364e-05,
"loss": 3.7217,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167645573169685e-05,
"loss": 3.7216,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166806978418633e-05,
"loss": 3.7294,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165968383667581e-05,
"loss": 3.722,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165129788916529e-05,
"loss": 3.7218,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.16429283204585e-05,
"loss": 3.7113,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.163454237294798e-05,
"loss": 3.7118,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.162615642543746e-05,
"loss": 3.7213,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161777047792694e-05,
"loss": 3.7169,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1609400909220156e-05,
"loss": 3.7055,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1601014961709636e-05,
"loss": 3.736,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.1592645393002846e-05,
"loss": 3.7126,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.1584259445492325e-05,
"loss": 3.7161,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.1575873497981805e-05,
"loss": 3.7117,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.1567487550471285e-05,
"loss": 3.7192,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.1559101602960765e-05,
"loss": 3.7214,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.1550715655450245e-05,
"loss": 3.7144,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.1542329707939725e-05,
"loss": 3.7209,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.1533943760429205e-05,
"loss": 3.7279,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.1525574191722414e-05,
"loss": 3.7191,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.1517188244211894e-05,
"loss": 3.7274,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.1508802296701374e-05,
"loss": 3.7121,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.1500416349190854e-05,
"loss": 3.7249,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149204678048407e-05,
"loss": 3.7109,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148366083297355e-05,
"loss": 3.7227,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147527488546303e-05,
"loss": 3.7119,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.146688893795251e-05,
"loss": 3.7245,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.145851936924572e-05,
"loss": 3.7208,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.14501334217352e-05,
"loss": 3.7178,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.144174747422468e-05,
"loss": 3.7062,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.143336152671416e-05,
"loss": 3.7124,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.142499195800737e-05,
"loss": 3.7108,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.141660601049685e-05,
"loss": 3.7232,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140822006298633e-05,
"loss": 3.7118,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139983411547581e-05,
"loss": 3.7282,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.1391464546769024e-05,
"loss": 3.7068,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.1383078599258504e-05,
"loss": 3.7199,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.1374692651747984e-05,
"loss": 3.7213,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.1366306704237464e-05,
"loss": 3.7258,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135793713553067e-05,
"loss": 3.7179,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134955118802015e-05,
"loss": 3.7174,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134116524050963e-05,
"loss": 3.7095,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133277929299911e-05,
"loss": 3.7317,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132440972429232e-05,
"loss": 3.705,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.13160237767818e-05,
"loss": 3.7208,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130763782927128e-05,
"loss": 3.7129,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129925188176076e-05,
"loss": 3.7216,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.1290898691857707e-05,
"loss": 3.7162,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.1282512744347186e-05,
"loss": 3.713,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.1274126796836666e-05,
"loss": 3.7169,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.1265740849326146e-05,
"loss": 3.7007,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.1257354901815626e-05,
"loss": 3.7186,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.861588954925537,
"eval_runtime": 302.8093,
"eval_samples_per_second": 1260.169,
"eval_steps_per_second": 39.381,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.1248968954305106e-05,
"loss": 3.7079,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.1240583006794586e-05,
"loss": 3.7024,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.1232197059284066e-05,
"loss": 3.7181,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.1223827490577275e-05,
"loss": 3.7178,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.1215457921870484e-05,
"loss": 3.724,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.1207071974359964e-05,
"loss": 3.7131,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.119868602684945e-05,
"loss": 3.7098,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.119030007933893e-05,
"loss": 3.7072,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.118191413182841e-05,
"loss": 3.7073,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117352818431789e-05,
"loss": 3.7169,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.11651586156111e-05,
"loss": 3.7098,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.115677266810058e-05,
"loss": 3.7135,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114840309939379e-05,
"loss": 3.7097,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.114001715188327e-05,
"loss": 3.703,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113163120437275e-05,
"loss": 3.6982,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112324525686223e-05,
"loss": 3.6996,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111485930935171e-05,
"loss": 3.714,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110647336184119e-05,
"loss": 3.7101,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109808741433067e-05,
"loss": 3.7048,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108970146682015e-05,
"loss": 3.7254,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108131551930963e-05,
"loss": 3.7192,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.107292957179911e-05,
"loss": 3.707,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.106454362428859e-05,
"loss": 3.708,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.105615767677807e-05,
"loss": 3.7047,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.104778810807128e-05,
"loss": 3.7067,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.103940216056076e-05,
"loss": 3.7054,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.103101621305024e-05,
"loss": 3.7091,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102263026553972e-05,
"loss": 3.7081,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101426069683293e-05,
"loss": 3.6975,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.100587474932241e-05,
"loss": 3.6967,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.0997488801811887e-05,
"loss": 3.6933,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.098910285430137e-05,
"loss": 3.71,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.098073328559458e-05,
"loss": 3.7154,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.097234733808406e-05,
"loss": 3.7106,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096396139057354e-05,
"loss": 3.6993,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095557544306302e-05,
"loss": 3.6972,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094720587435623e-05,
"loss": 3.7108,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.093883630564944e-05,
"loss": 3.6965,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.093045035813892e-05,
"loss": 3.6948,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.09220644106284e-05,
"loss": 3.6995,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.091367846311788e-05,
"loss": 3.695,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.090529251560736e-05,
"loss": 3.7059,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089690656809684e-05,
"loss": 3.7014,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088852062058633e-05,
"loss": 3.7058,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.088013467307581e-05,
"loss": 3.6989,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.0871765104369016e-05,
"loss": 3.7045,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.0863379156858496e-05,
"loss": 3.7071,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.0854993209347976e-05,
"loss": 3.6902,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.0846607261837456e-05,
"loss": 3.6684,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.0838237693130665e-05,
"loss": 3.7145,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.0829851745620145e-05,
"loss": 3.6981,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.0821465798109625e-05,
"loss": 3.7037,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.0813079850599105e-05,
"loss": 3.6959,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.0804710281892314e-05,
"loss": 3.6968,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.0796324334381794e-05,
"loss": 3.6831,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.0787938386871274e-05,
"loss": 3.6975,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077956881816449e-05,
"loss": 3.7055,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077118287065397e-05,
"loss": 3.685,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.076279692314345e-05,
"loss": 3.7125,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075441097563293e-05,
"loss": 3.6954,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.074604140692614e-05,
"loss": 3.6805,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.073765545941562e-05,
"loss": 3.6958,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.07292695119051e-05,
"loss": 3.6848,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.072088356439458e-05,
"loss": 3.6803,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071251399568779e-05,
"loss": 3.7019,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.070412804817727e-05,
"loss": 3.7003,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.069574210066675e-05,
"loss": 3.6895,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.068735615315623e-05,
"loss": 3.6976,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.0678986584449443e-05,
"loss": 3.6751,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.067060063693892e-05,
"loss": 3.7,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.06622146894284e-05,
"loss": 3.6916,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.065382874191788e-05,
"loss": 3.6942,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064545917321109e-05,
"loss": 3.7016,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.063707322570057e-05,
"loss": 3.6929,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.062868727819005e-05,
"loss": 3.712,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.062030133067953e-05,
"loss": 3.683,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.061193176197274e-05,
"loss": 3.6993,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060354581446222e-05,
"loss": 3.6924,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.05951598669517e-05,
"loss": 3.686,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.058679029824492e-05,
"loss": 3.7028,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.05784043507344e-05,
"loss": 3.7047,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.057001840322388e-05,
"loss": 3.6983,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056163245571336e-05,
"loss": 3.7099,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055324650820284e-05,
"loss": 3.6844,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.054486056069232e-05,
"loss": 3.6814,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.05364746131818e-05,
"loss": 3.6915,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.052808866567128e-05,
"loss": 3.7042,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.0519719096964486e-05,
"loss": 3.6894,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.0511333149453966e-05,
"loss": 3.6952,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.0502947201943446e-05,
"loss": 3.6903,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.0494577633236655e-05,
"loss": 3.6994,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.0486191685726135e-05,
"loss": 3.6894,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.047780573821562e-05,
"loss": 3.6865,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.04694197907051e-05,
"loss": 3.6929,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.0461033843194575e-05,
"loss": 3.7051,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.0452647895684055e-05,
"loss": 3.6949,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.0444261948173535e-05,
"loss": 3.6747,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043589237946675e-05,
"loss": 3.6895,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.0427506431956224e-05,
"loss": 3.6891,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.0419120484445704e-05,
"loss": 3.6983,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.041075091573892e-05,
"loss": 3.6924,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.04023649682284e-05,
"loss": 3.6872,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039397902071787e-05,
"loss": 3.682,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038559307320736e-05,
"loss": 3.6788,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.037720712569684e-05,
"loss": 3.689,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036882117818632e-05,
"loss": 3.6852,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.03604352306758e-05,
"loss": 3.6758,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.035206566196901e-05,
"loss": 3.7013,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0343696093262224e-05,
"loss": 3.6856,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.03353101457517e-05,
"loss": 3.6831,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.032692419824118e-05,
"loss": 3.6838,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.031853825073066e-05,
"loss": 3.6826,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.031015230322014e-05,
"loss": 3.6914,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030176635570962e-05,
"loss": 3.682,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.02933804081991e-05,
"loss": 3.6933,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028499446068858e-05,
"loss": 3.6967,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027662489198179e-05,
"loss": 3.687,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026823894447127e-05,
"loss": 3.6941,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025985299696075e-05,
"loss": 3.6828,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025146704945023e-05,
"loss": 3.6953,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024308110193971e-05,
"loss": 3.6811,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023469515442919e-05,
"loss": 3.6851,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022630920691867e-05,
"loss": 3.6836,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021793963821188e-05,
"loss": 3.6956,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020955369070136e-05,
"loss": 3.6944,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.020116774319084e-05,
"loss": 3.6842,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.019278179568032e-05,
"loss": 3.6706,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.01843958481698e-05,
"loss": 3.6865,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017600990065928e-05,
"loss": 3.6791,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.016762395314876e-05,
"loss": 3.6901,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.015925438444198e-05,
"loss": 3.6832,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015086843693146e-05,
"loss": 3.6969,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.014248248942094e-05,
"loss": 3.6763,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013409654191041e-05,
"loss": 3.6925,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012571059439989e-05,
"loss": 3.6886,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011732464688937e-05,
"loss": 3.6975,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010893869937885e-05,
"loss": 3.6873,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.010055275186833e-05,
"loss": 3.6823,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009218318316154e-05,
"loss": 3.6836,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008379723565102e-05,
"loss": 3.6998,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.00754112881405e-05,
"loss": 3.6732,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006702534062998e-05,
"loss": 3.6909,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.0058655771923195e-05,
"loss": 3.6866,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.0050269824412675e-05,
"loss": 3.687,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.0041900255705884e-05,
"loss": 3.6842,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.0033514308195364e-05,
"loss": 3.6866,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.0025128360684844e-05,
"loss": 3.685,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.0016742413174324e-05,
"loss": 3.674,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000837284446753e-05,
"loss": 3.6853,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 3.854919910430908,
"eval_runtime": 302.963,
"eval_samples_per_second": 1259.53,
"eval_steps_per_second": 39.361,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999998689695701e-05,
"loss": 3.675,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999160094944649e-05,
"loss": 3.675,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998321500193597e-05,
"loss": 3.6875,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997482905442545e-05,
"loss": 3.6875,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996645948571867e-05,
"loss": 3.6975,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995807353820815e-05,
"loss": 3.6781,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994968759069763e-05,
"loss": 3.6815,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994130164318711e-05,
"loss": 3.6797,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993291569567659e-05,
"loss": 3.676,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992452974816607e-05,
"loss": 3.6905,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991616017945928e-05,
"loss": 3.6788,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990777423194876e-05,
"loss": 3.682,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989940466324197e-05,
"loss": 3.6861,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.989101871573145e-05,
"loss": 3.6671,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.988263276822093e-05,
"loss": 3.67,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.987424682071041e-05,
"loss": 3.6676,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986586087319989e-05,
"loss": 3.6856,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.985747492568937e-05,
"loss": 3.6773,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.984908897817885e-05,
"loss": 3.6768,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.984070303066833e-05,
"loss": 3.6935,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983231708315781e-05,
"loss": 3.6894,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.982393113564729e-05,
"loss": 3.6754,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981554518813677e-05,
"loss": 3.6788,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.9807159240626246e-05,
"loss": 3.6769,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979878967191946e-05,
"loss": 3.6783,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.979040372440894e-05,
"loss": 3.6732,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.978201777689842e-05,
"loss": 3.6758,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.9773631829387895e-05,
"loss": 3.6849,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976526226068111e-05,
"loss": 3.667,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975687631317059e-05,
"loss": 3.6652,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974849036566007e-05,
"loss": 3.6698,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.974012079695329e-05,
"loss": 3.6757,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973173484944277e-05,
"loss": 3.6825,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972334890193225e-05,
"loss": 3.6893,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971496295442172e-05,
"loss": 3.6696,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.97065770069112e-05,
"loss": 3.6717,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969819105940068e-05,
"loss": 3.6834,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.9689821490693896e-05,
"loss": 3.6658,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968143554318337e-05,
"loss": 3.6656,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967304959567285e-05,
"loss": 3.674,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966466364816233e-05,
"loss": 3.6642,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965627770065181e-05,
"loss": 3.6737,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964789175314129e-05,
"loss": 3.6748,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.9639505805630776e-05,
"loss": 3.6779,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9631119858120256e-05,
"loss": 3.6663,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.9622750289413465e-05,
"loss": 3.6795,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.9614364341902945e-05,
"loss": 3.6762,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.9605978394392425e-05,
"loss": 3.665,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.9597592446881905e-05,
"loss": 3.643,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.9589222878175114e-05,
"loss": 3.6819,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.9580836930664594e-05,
"loss": 3.6675,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.9572450983154074e-05,
"loss": 3.6754,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.9564065035643553e-05,
"loss": 3.6687,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955569546693676e-05,
"loss": 3.6636,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954730951942624e-05,
"loss": 3.6604,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953892357191572e-05,
"loss": 3.6664,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.953055400320894e-05,
"loss": 3.6808,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952218443450215e-05,
"loss": 3.6548,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951379848699163e-05,
"loss": 3.6878,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950541253948111e-05,
"loss": 3.667,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949702659197059e-05,
"loss": 3.6518,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948864064446007e-05,
"loss": 3.669,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.948025469694955e-05,
"loss": 3.6551,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947186874943903e-05,
"loss": 3.6542,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946348280192851e-05,
"loss": 3.6704,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945512961202545e-05,
"loss": 3.6737,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.944674366451493e-05,
"loss": 3.6571,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.943835771700441e-05,
"loss": 3.6736,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942997176949389e-05,
"loss": 3.6462,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.942158582198337e-05,
"loss": 3.6691,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941319987447285e-05,
"loss": 3.6647,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940481392696233e-05,
"loss": 3.6649,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939644435825554e-05,
"loss": 3.6748,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938805841074502e-05,
"loss": 3.6657,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.93796724632345e-05,
"loss": 3.6848,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937128651572398e-05,
"loss": 3.6574,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936290056821346e-05,
"loss": 3.6706,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935451462070294e-05,
"loss": 3.6619,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934612867319242e-05,
"loss": 3.6593,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933775910448563e-05,
"loss": 3.6773,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.9329373156975117e-05,
"loss": 3.6725,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.9320987209464596e-05,
"loss": 3.6747,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.9312601261954076e-05,
"loss": 3.6815,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.9304215314443556e-05,
"loss": 3.6589,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.9295845745736766e-05,
"loss": 3.6534,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.9287459798226245e-05,
"loss": 3.6631,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.9279073850715725e-05,
"loss": 3.6768,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.92706879032052e-05,
"loss": 3.6607,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926230195569468e-05,
"loss": 3.6661,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.9253932386987894e-05,
"loss": 3.6681,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.9245546439477374e-05,
"loss": 3.667,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.9237160491966854e-05,
"loss": 3.6649,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.9228774544456334e-05,
"loss": 3.6571,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9220388596945814e-05,
"loss": 3.6662,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9212002649435294e-05,
"loss": 3.6768,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9203616701924774e-05,
"loss": 3.6694,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9195230754414254e-05,
"loss": 3.6506,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.918686118570746e-05,
"loss": 3.6605,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.917847523819694e-05,
"loss": 3.6612,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.917008929068642e-05,
"loss": 3.6688,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916171972197963e-05,
"loss": 3.6688,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915333377446911e-05,
"loss": 3.6589,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914494782695859e-05,
"loss": 3.6574,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913656187944807e-05,
"loss": 3.6487,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912819231074129e-05,
"loss": 3.6615,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911980636323077e-05,
"loss": 3.6601,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911142041572025e-05,
"loss": 3.6518,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.910303446820973e-05,
"loss": 3.6712,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909464852069921e-05,
"loss": 3.6551,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908627895199242e-05,
"loss": 3.6576,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.90778930044819e-05,
"loss": 3.6533,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906950705697138e-05,
"loss": 3.6539,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.906112110946086e-05,
"loss": 3.6675,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905273516195034e-05,
"loss": 3.6525,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904434921443982e-05,
"loss": 3.6659,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.9035963266929297e-05,
"loss": 3.6707,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9027593698222506e-05,
"loss": 3.6613,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.901920775071199e-05,
"loss": 3.6678,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.901082180320147e-05,
"loss": 3.6548,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900243585569095e-05,
"loss": 3.6683,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899404990818043e-05,
"loss": 3.6582,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898566396066991e-05,
"loss": 3.6593,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897727801315939e-05,
"loss": 3.6585,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.89689084444526e-05,
"loss": 3.6655,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.896052249694208e-05,
"loss": 3.6697,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895213654943156e-05,
"loss": 3.6538,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.8943750601921034e-05,
"loss": 3.6485,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.8935364654410514e-05,
"loss": 3.6543,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926978706899994e-05,
"loss": 3.6554,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8918592759389474e-05,
"loss": 3.6642,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.891022319068269e-05,
"loss": 3.6566,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.890183724317217e-05,
"loss": 3.6673,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889345129566165e-05,
"loss": 3.6498,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888506534815113e-05,
"loss": 3.6708,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887667940064061e-05,
"loss": 3.6582,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886829345313009e-05,
"loss": 3.6671,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885990750561957e-05,
"loss": 3.6595,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885152155810905e-05,
"loss": 3.6546,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884315198940226e-05,
"loss": 3.6571,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883476604189174e-05,
"loss": 3.6751,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882638009438122e-05,
"loss": 3.6503,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.88179941468707e-05,
"loss": 3.6644,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880962457816391e-05,
"loss": 3.659,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.8801238630653395e-05,
"loss": 3.6614,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.8792869061946604e-05,
"loss": 3.6585,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.8784483114436084e-05,
"loss": 3.6586,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.8776097166925564e-05,
"loss": 3.6565,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.8767711219415044e-05,
"loss": 3.6564,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875934165070825e-05,
"loss": 3.6566,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.8491063117980957,
"eval_runtime": 304.7266,
"eval_samples_per_second": 1252.241,
"eval_steps_per_second": 39.133,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875095570319773e-05,
"loss": 3.6477,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874256975568721e-05,
"loss": 3.6474,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873418380817669e-05,
"loss": 3.6588,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.872579786066617e-05,
"loss": 3.6626,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.871742829195938e-05,
"loss": 3.6722,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.870904234444886e-05,
"loss": 3.6495,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.870065639693835e-05,
"loss": 3.6571,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869227044942783e-05,
"loss": 3.6549,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868388450191731e-05,
"loss": 3.6473,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.867549855440679e-05,
"loss": 3.6634,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.86671289857e-05,
"loss": 3.6509,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.865874303818948e-05,
"loss": 3.6575,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.8650373469482686e-05,
"loss": 3.6618,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641987521972166e-05,
"loss": 3.6429,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8633601574461646e-05,
"loss": 3.6418,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8625215626951126e-05,
"loss": 3.6434,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.8616829679440606e-05,
"loss": 3.6571,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.8608443731930086e-05,
"loss": 3.6588,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.8600057784419566e-05,
"loss": 3.6432,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.8591671836909046e-05,
"loss": 3.6664,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858330226820226e-05,
"loss": 3.663,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857491632069174e-05,
"loss": 3.6503,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856653037318122e-05,
"loss": 3.6532,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.8558144425670695e-05,
"loss": 3.652,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854977485696391e-05,
"loss": 3.6527,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854138890945339e-05,
"loss": 3.6492,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853300296194287e-05,
"loss": 3.6469,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.8524617014432344e-05,
"loss": 3.6576,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.8516231066921824e-05,
"loss": 3.6426,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.8507845119411304e-05,
"loss": 3.6395,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849947555070452e-05,
"loss": 3.6445,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.8491089603194e-05,
"loss": 3.6508,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848270365568348e-05,
"loss": 3.652,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847431770817296e-05,
"loss": 3.6639,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846593176066244e-05,
"loss": 3.6448,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845754581315192e-05,
"loss": 3.6452,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.84491598656414e-05,
"loss": 3.6617,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.844079029693461e-05,
"loss": 3.6381,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843240434942409e-05,
"loss": 3.6425,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842401840191357e-05,
"loss": 3.6485,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841563245440305e-05,
"loss": 3.6384,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840724650689253e-05,
"loss": 3.6444,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839886055938201e-05,
"loss": 3.6499,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.839047461187149e-05,
"loss": 3.6531,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.8382105043164704e-05,
"loss": 3.6417,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.8373719095654184e-05,
"loss": 3.654,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.8365333148143664e-05,
"loss": 3.648,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.8356947200633144e-05,
"loss": 3.6415,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.8348561253122624e-05,
"loss": 3.621,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.8340175305612104e-05,
"loss": 3.6558,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833180573690531e-05,
"loss": 3.6448,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832341978939479e-05,
"loss": 3.6532,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.831503384188427e-05,
"loss": 3.6372,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.830664789437375e-05,
"loss": 3.6399,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829826194686323e-05,
"loss": 3.634,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828989237815644e-05,
"loss": 3.64,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828150643064592e-05,
"loss": 3.6591,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.82731204831354e-05,
"loss": 3.6312,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826473453562489e-05,
"loss": 3.6587,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825634858811436e-05,
"loss": 3.645,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824796264060384e-05,
"loss": 3.6262,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.823957669309332e-05,
"loss": 3.6398,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.823120712438653e-05,
"loss": 3.6286,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.822282117687601e-05,
"loss": 3.633,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.821443522936549e-05,
"loss": 3.6428,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.820604928185497e-05,
"loss": 3.6492,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.819767971314818e-05,
"loss": 3.6327,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.818929376563766e-05,
"loss": 3.647,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818090781812714e-05,
"loss": 3.6248,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.8172521870616626e-05,
"loss": 3.6446,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.8164135923106106e-05,
"loss": 3.6416,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.8155749975595586e-05,
"loss": 3.6435,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.8147380406888795e-05,
"loss": 3.6439,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.8138994459378275e-05,
"loss": 3.6422,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.8130608511867755e-05,
"loss": 3.6588,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.8122222564357235e-05,
"loss": 3.6321,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.8113852995650444e-05,
"loss": 3.6481,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.8105467048139924e-05,
"loss": 3.6382,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.8097081100629404e-05,
"loss": 3.6315,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.8088695153118884e-05,
"loss": 3.6486,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.8080309205608364e-05,
"loss": 3.6491,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807193963690158e-05,
"loss": 3.6482,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806355368939106e-05,
"loss": 3.6569,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805516774188054e-05,
"loss": 3.6363,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804678179437002e-05,
"loss": 3.6274,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.80383958468595e-05,
"loss": 3.6365,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.803000989934898e-05,
"loss": 3.6491,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.802162395183846e-05,
"loss": 3.6381,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.801325438313167e-05,
"loss": 3.6435,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.800486843562115e-05,
"loss": 3.6403,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799648248811063e-05,
"loss": 3.644,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.798809654060011e-05,
"loss": 3.6412,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797972697189332e-05,
"loss": 3.633,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.79713410243828e-05,
"loss": 3.6414,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796295507687228e-05,
"loss": 3.6533,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.7954569129361764e-05,
"loss": 3.644,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.7946183181851244e-05,
"loss": 3.624,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.7937813613144454e-05,
"loss": 3.6389,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.7929427665633933e-05,
"loss": 3.6392,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.7921041718123413e-05,
"loss": 3.6444,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.7912655770612893e-05,
"loss": 3.6438,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.7904269823102367e-05,
"loss": 3.633,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.7895883875591847e-05,
"loss": 3.6341,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788751430688506e-05,
"loss": 3.6263,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.787912835937454e-05,
"loss": 3.6385,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.7870742411864016e-05,
"loss": 3.6336,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.78623564643535e-05,
"loss": 3.6287,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785397051684298e-05,
"loss": 3.6408,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784560094813619e-05,
"loss": 3.6374,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783721500062567e-05,
"loss": 3.633,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782882905311515e-05,
"loss": 3.6317,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.782044310560463e-05,
"loss": 3.6283,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781205715809411e-05,
"loss": 3.6446,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.780367121058359e-05,
"loss": 3.625,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.779528526307307e-05,
"loss": 3.6439,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778691569436628e-05,
"loss": 3.6462,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777852974685576e-05,
"loss": 3.6378,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.777014379934524e-05,
"loss": 3.6441,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776175785183472e-05,
"loss": 3.635,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.7753388283127936e-05,
"loss": 3.6431,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.7745002335617416e-05,
"loss": 3.6356,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.7736616388106896e-05,
"loss": 3.6325,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.7728230440596376e-05,
"loss": 3.6363,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.7719844493085856e-05,
"loss": 3.6392,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.7711474924379065e-05,
"loss": 3.6429,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.7703088976868545e-05,
"loss": 3.6327,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.7694703029358025e-05,
"loss": 3.6242,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.7686317081847505e-05,
"loss": 3.6348,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.7677931134336985e-05,
"loss": 3.6256,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.7669545186826465e-05,
"loss": 3.6437,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.7661175618119674e-05,
"loss": 3.6325,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.7652789670609154e-05,
"loss": 3.6423,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.7644403723098634e-05,
"loss": 3.6256,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.763601777558812e-05,
"loss": 3.6464,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.76276318280776e-05,
"loss": 3.6324,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761924588056708e-05,
"loss": 3.6481,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.761087631186029e-05,
"loss": 3.6365,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760249036434977e-05,
"loss": 3.633,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759410441683925e-05,
"loss": 3.6297,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758571846932873e-05,
"loss": 3.6528,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.75773325218182e-05,
"loss": 3.6216,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.756894657430768e-05,
"loss": 3.6426,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.75605770056009e-05,
"loss": 3.6338,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755219105809038e-05,
"loss": 3.6357,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754380511057986e-05,
"loss": 3.6376,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.753541916306934e-05,
"loss": 3.631,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.7527049594362554e-05,
"loss": 3.635,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751866364685203e-05,
"loss": 3.633,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.751027769934151e-05,
"loss": 3.6299,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 3.8466107845306396,
"eval_runtime": 302.6188,
"eval_samples_per_second": 1260.962,
"eval_steps_per_second": 39.406,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750189175183099e-05,
"loss": 3.6191,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.749350580432047e-05,
"loss": 3.6252,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748511985680995e-05,
"loss": 3.6356,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747673390929943e-05,
"loss": 3.6413,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.7468364340592636e-05,
"loss": 3.6482,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.7459978393082116e-05,
"loss": 3.6279,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.7451592445571596e-05,
"loss": 3.6296,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.7443206498061076e-05,
"loss": 3.6359,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.7434820550550556e-05,
"loss": 3.6244,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742645098184377e-05,
"loss": 3.633,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741806503433325e-05,
"loss": 3.635,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740967908682273e-05,
"loss": 3.6347,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740130951811594e-05,
"loss": 3.6377,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739292357060542e-05,
"loss": 3.6199,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.73845376230949e-05,
"loss": 3.6186,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737615167558438e-05,
"loss": 3.6172,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736776572807386e-05,
"loss": 3.6411,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735937978056334e-05,
"loss": 3.632,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735099383305282e-05,
"loss": 3.6213,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.73426078855423e-05,
"loss": 3.6408,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733423831683551e-05,
"loss": 3.6436,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.7325852369324996e-05,
"loss": 3.6299,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.7317466421814476e-05,
"loss": 3.6294,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.7309080474303956e-05,
"loss": 3.6276,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7300710905597165e-05,
"loss": 3.6366,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.7292324958086645e-05,
"loss": 3.6261,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283939010576125e-05,
"loss": 3.6213,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.7275553063065605e-05,
"loss": 3.6377,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.7267167115555085e-05,
"loss": 3.6187,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.7258781168044565e-05,
"loss": 3.6147,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.7250411599337774e-05,
"loss": 3.6271,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.7242025651827254e-05,
"loss": 3.6253,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.7233639704316734e-05,
"loss": 3.6324,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.7225253756806214e-05,
"loss": 3.6408,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721688418809943e-05,
"loss": 3.6197,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720849824058891e-05,
"loss": 3.6264,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.720011229307839e-05,
"loss": 3.6372,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719172634556786e-05,
"loss": 3.6145,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718335677686108e-05,
"loss": 3.6212,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717497082935056e-05,
"loss": 3.6257,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716658488184004e-05,
"loss": 3.6165,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715819893432951e-05,
"loss": 3.6237,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.714981298681899e-05,
"loss": 3.6298,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714142703930847e-05,
"loss": 3.631,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713305747060168e-05,
"loss": 3.6209,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712467152309117e-05,
"loss": 3.6279,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711628557558065e-05,
"loss": 3.6267,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710789962807013e-05,
"loss": 3.6227,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709951368055961e-05,
"loss": 3.598,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.7091144111852817e-05,
"loss": 3.6307,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.7082758164342297e-05,
"loss": 3.6252,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.7074372216831777e-05,
"loss": 3.6286,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.7065986269321256e-05,
"loss": 3.6197,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.7057600321810736e-05,
"loss": 3.6143,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.7049230753103946e-05,
"loss": 3.6148,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.7040844805593425e-05,
"loss": 3.6187,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.7032458858082905e-05,
"loss": 3.6341,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.7024072910572385e-05,
"loss": 3.6106,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.7015686963061865e-05,
"loss": 3.6332,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.700731739435508e-05,
"loss": 3.6271,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699893144684456e-05,
"loss": 3.6061,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.699054549933404e-05,
"loss": 3.621,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698215955182352e-05,
"loss": 3.6049,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.6973773604313e-05,
"loss": 3.6112,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696538765680248e-05,
"loss": 3.6166,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695701808809569e-05,
"loss": 3.6306,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694863214058517e-05,
"loss": 3.6117,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.694024619307465e-05,
"loss": 3.6248,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693186024556413e-05,
"loss": 3.6024,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692347429805361e-05,
"loss": 3.619,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691508835054309e-05,
"loss": 3.6187,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690670240303257e-05,
"loss": 3.6241,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.6898332834325786e-05,
"loss": 3.6204,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.6889946886815266e-05,
"loss": 3.6186,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.6881560939304746e-05,
"loss": 3.6368,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.6873174991794226e-05,
"loss": 3.6106,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.6864805423087435e-05,
"loss": 3.6232,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.6856419475576915e-05,
"loss": 3.6142,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.6848033528066395e-05,
"loss": 3.6154,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683964758055587e-05,
"loss": 3.6285,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.6831278011849084e-05,
"loss": 3.6212,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.6822892064338564e-05,
"loss": 3.6274,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.6814506116828044e-05,
"loss": 3.6354,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.6806120169317523e-05,
"loss": 3.623,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.6797734221807003e-05,
"loss": 3.6026,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.6789348274296483e-05,
"loss": 3.6135,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.67809787055897e-05,
"loss": 3.6272,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677259275807917e-05,
"loss": 3.6173,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676420681056865e-05,
"loss": 3.6206,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675582086305813e-05,
"loss": 3.6197,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.674745129435134e-05,
"loss": 3.621,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.673906534684082e-05,
"loss": 3.6185,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.67306793993303e-05,
"loss": 3.6123,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672229345181978e-05,
"loss": 3.6228,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671390750430926e-05,
"loss": 3.6292,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670552155679874e-05,
"loss": 3.6235,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669715198809196e-05,
"loss": 3.6014,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668876604058144e-05,
"loss": 3.6176,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.668038009307092e-05,
"loss": 3.62,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.66719941455604e-05,
"loss": 3.6215,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.6663624576853606e-05,
"loss": 3.6219,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.6655238629343086e-05,
"loss": 3.6103,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.6646852681832566e-05,
"loss": 3.6101,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.6638466734322046e-05,
"loss": 3.6061,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.6630097165615255e-05,
"loss": 3.6147,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.6621711218104735e-05,
"loss": 3.6141,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.6613325270594215e-05,
"loss": 3.6106,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6604939323083695e-05,
"loss": 3.6225,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.659656975437691e-05,
"loss": 3.6127,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.658818380686639e-05,
"loss": 3.6101,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.657979785935587e-05,
"loss": 3.612,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.657141191184535e-05,
"loss": 3.6049,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656302596433483e-05,
"loss": 3.6207,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655464001682431e-05,
"loss": 3.6097,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654625406931379e-05,
"loss": 3.6166,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.6537884500607e-05,
"loss": 3.6237,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652949855309648e-05,
"loss": 3.6179,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652111260558596e-05,
"loss": 3.6177,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651272665807544e-05,
"loss": 3.6162,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650435708936865e-05,
"loss": 3.618,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649597114185813e-05,
"loss": 3.6206,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.6487585194347615e-05,
"loss": 3.6112,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.6479199246837095e-05,
"loss": 3.6138,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.6470829678130304e-05,
"loss": 3.6185,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.6462443730619784e-05,
"loss": 3.6222,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6454057783109264e-05,
"loss": 3.6092,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.6445671835598744e-05,
"loss": 3.6043,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.6437285888088224e-05,
"loss": 3.6093,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.6428899940577704e-05,
"loss": 3.6051,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.642051399306718e-05,
"loss": 3.6227,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641214442436039e-05,
"loss": 3.6126,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640375847684987e-05,
"loss": 3.622,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639537252933935e-05,
"loss": 3.6087,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638698658182883e-05,
"loss": 3.6201,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637860063431831e-05,
"loss": 3.6112,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.637021468680779e-05,
"loss": 3.6279,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636184511810101e-05,
"loss": 3.6141,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635345917059048e-05,
"loss": 3.612,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634507322307996e-05,
"loss": 3.6108,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633668727556944e-05,
"loss": 3.6287,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632830132805892e-05,
"loss": 3.6063,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.63199153805484e-05,
"loss": 3.618,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631154581184161e-05,
"loss": 3.6152,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630315986433109e-05,
"loss": 3.6152,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629477391682057e-05,
"loss": 3.6165,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628638796931005e-05,
"loss": 3.6127,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627801840060327e-05,
"loss": 3.6132,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.6269632453092747e-05,
"loss": 3.6146,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.6261246505582227e-05,
"loss": 3.6088,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.844973087310791,
"eval_runtime": 304.7522,
"eval_samples_per_second": 1252.135,
"eval_steps_per_second": 39.13,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.6252860558071707e-05,
"loss": 3.6041,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.6244474610561186e-05,
"loss": 3.6047,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.6236105041854396e-05,
"loss": 3.6133,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.6227719094343876e-05,
"loss": 3.6221,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.6219333146833355e-05,
"loss": 3.6271,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.6210947199322835e-05,
"loss": 3.6071,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.6202561251812315e-05,
"loss": 3.6126,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.6194175304301795e-05,
"loss": 3.6156,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.6185789356791275e-05,
"loss": 3.6049,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.617741978808449e-05,
"loss": 3.6067,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.616903384057397e-05,
"loss": 3.6197,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.616064789306345e-05,
"loss": 3.6123,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.615227832435666e-05,
"loss": 3.6169,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.614389237684614e-05,
"loss": 3.5966,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.613550642933562e-05,
"loss": 3.598,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.61271204818251e-05,
"loss": 3.5987,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.611873453431458e-05,
"loss": 3.6172,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.611034858680406e-05,
"loss": 3.6134,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.610196263929354e-05,
"loss": 3.6025,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.609357669178301e-05,
"loss": 3.6186,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.608520712307623e-05,
"loss": 3.6236,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.607682117556571e-05,
"loss": 3.606,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.606843522805519e-05,
"loss": 3.61,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.606004928054467e-05,
"loss": 3.6075,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.6051679711837885e-05,
"loss": 3.6167,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.6043293764327365e-05,
"loss": 3.603,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.603490781681684e-05,
"loss": 3.6006,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.602652186930632e-05,
"loss": 3.6208,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.60181359217958e-05,
"loss": 3.5958,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.600974997428528e-05,
"loss": 3.5958,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.600138040557849e-05,
"loss": 3.6032,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.599299445806797e-05,
"loss": 3.6047,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598460851055745e-05,
"loss": 3.6143,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.597622256304693e-05,
"loss": 3.6208,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596783661553641e-05,
"loss": 3.596,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595946704682962e-05,
"loss": 3.6079,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.59510810993191e-05,
"loss": 3.6155,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.594269515180858e-05,
"loss": 3.5918,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.593430920429806e-05,
"loss": 3.5995,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.592593963559127e-05,
"loss": 3.6084,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.591755368808075e-05,
"loss": 3.5916,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.590916774057023e-05,
"loss": 3.6057,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.590078179305971e-05,
"loss": 3.6108,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.589239584554919e-05,
"loss": 3.6086,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.58840262768424e-05,
"loss": 3.5987,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.587564032933188e-05,
"loss": 3.6075,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.586725438182136e-05,
"loss": 3.6044,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.585886843431085e-05,
"loss": 3.6039,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.585048248680033e-05,
"loss": 3.5793,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.5842112918093536e-05,
"loss": 3.6088,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.5833726970583016e-05,
"loss": 3.6068,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.5825341023072496e-05,
"loss": 3.6061,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.5816955075561976e-05,
"loss": 3.5986,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.5808585506855185e-05,
"loss": 3.5956,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.5800199559344665e-05,
"loss": 3.594,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.5791813611834145e-05,
"loss": 3.5966,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.5783427664323625e-05,
"loss": 3.6175,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.5775041716813105e-05,
"loss": 3.591,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.5766672148106314e-05,
"loss": 3.6066,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.57582862005958e-05,
"loss": 3.6065,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.574990025308528e-05,
"loss": 3.5887,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.574151430557476e-05,
"loss": 3.5972,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.573312835806424e-05,
"loss": 3.5889,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.572475878935745e-05,
"loss": 3.5928,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.571637284184693e-05,
"loss": 3.5919,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.570798689433641e-05,
"loss": 3.6134,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.569960094682589e-05,
"loss": 3.5944,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.569121499931537e-05,
"loss": 3.5968,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.568284543060858e-05,
"loss": 3.5879,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567445948309806e-05,
"loss": 3.5973,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566607353558754e-05,
"loss": 3.6003,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565768758807702e-05,
"loss": 3.6017,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.56493016405665e-05,
"loss": 3.6048,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.5640932071859714e-05,
"loss": 3.6008,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.5632546124349194e-05,
"loss": 3.6122,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.5624160176838674e-05,
"loss": 3.5919,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.561577422932815e-05,
"loss": 3.6029,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.560740466062136e-05,
"loss": 3.5962,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.559901871311084e-05,
"loss": 3.5941,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.559063276560032e-05,
"loss": 3.6066,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.5582246818089796e-05,
"loss": 3.6004,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.557387724938301e-05,
"loss": 3.6102,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.556549130187249e-05,
"loss": 3.6142,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.555710535436197e-05,
"loss": 3.6069,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.554871940685145e-05,
"loss": 3.5838,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.554033345934093e-05,
"loss": 3.5961,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.553196389063415e-05,
"loss": 3.6036,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.552357794312362e-05,
"loss": 3.6027,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.55151919956131e-05,
"loss": 3.5959,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.550680604810258e-05,
"loss": 3.6,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.54984364793958e-05,
"loss": 3.6012,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.549005053188527e-05,
"loss": 3.5967,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548166458437475e-05,
"loss": 3.5931,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.547327863686423e-05,
"loss": 3.6029,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.5464909068157446e-05,
"loss": 3.6043,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.5456523120646926e-05,
"loss": 3.6094,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.5448137173136406e-05,
"loss": 3.5818,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.5439751225625886e-05,
"loss": 3.5964,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.5431365278115366e-05,
"loss": 3.5987,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.5422995709408575e-05,
"loss": 3.6038,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.5414609761898055e-05,
"loss": 3.6021,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.5406223814387535e-05,
"loss": 3.5913,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.5397837866877015e-05,
"loss": 3.5938,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.5389468298170224e-05,
"loss": 3.5815,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.5381082350659704e-05,
"loss": 3.601,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.5372696403149184e-05,
"loss": 3.5916,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.5364310455638664e-05,
"loss": 3.5888,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.5355924508128144e-05,
"loss": 3.6017,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.534755493942136e-05,
"loss": 3.596,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.533916899191084e-05,
"loss": 3.5887,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.533078304440032e-05,
"loss": 3.5955,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.53223970968898e-05,
"loss": 3.5836,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.531402752818301e-05,
"loss": 3.6051,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530564158067249e-05,
"loss": 3.5876,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529725563316197e-05,
"loss": 3.6012,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.528886968565145e-05,
"loss": 3.5962,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.528050011694466e-05,
"loss": 3.6026,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527211416943414e-05,
"loss": 3.5985,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.526372822192362e-05,
"loss": 3.5944,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.52553422744131e-05,
"loss": 3.6036,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524695632690258e-05,
"loss": 3.5981,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523858675819579e-05,
"loss": 3.5906,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.523020081068527e-05,
"loss": 3.5937,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.522181486317475e-05,
"loss": 3.5977,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.521342891566423e-05,
"loss": 3.6024,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.520504296815371e-05,
"loss": 3.5916,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.519667339944692e-05,
"loss": 3.5877,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.51882874519364e-05,
"loss": 3.589,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.517990150442588e-05,
"loss": 3.5872,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.517151555691536e-05,
"loss": 3.599,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.516314598820857e-05,
"loss": 3.5928,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.515476004069805e-05,
"loss": 3.606,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.514637409318753e-05,
"loss": 3.5859,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.513798814567702e-05,
"loss": 3.6033,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.512961857697023e-05,
"loss": 3.5954,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.5121232629459707e-05,
"loss": 3.603,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.5112846681949187e-05,
"loss": 3.5953,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.5104460734438666e-05,
"loss": 3.5929,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.5096074786928146e-05,
"loss": 3.5934,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.5087705218221356e-05,
"loss": 3.606,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.5079319270710836e-05,
"loss": 3.5894,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.5070933323200315e-05,
"loss": 3.5938,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.5062547375689795e-05,
"loss": 3.5996,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.5054177806983005e-05,
"loss": 3.5949,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.5045791859472484e-05,
"loss": 3.5944,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.503740591196197e-05,
"loss": 3.6014,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.502901996445145e-05,
"loss": 3.5906,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.502063401694093e-05,
"loss": 3.5926,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501226444823414e-05,
"loss": 3.5909,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 3.8433103561401367,
"eval_runtime": 304.381,
"eval_samples_per_second": 1253.662,
"eval_steps_per_second": 39.178,
"step": 915840
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.347677072250143e+17,
"trial_name": null,
"trial_params": null
}