abhinavp's picture
Training in progress, epoch 0, checkpoint
46f8a37 verified
{
"best_metric": 3.843820810317993,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/2/checkpoints/checkpoint-992160",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 1679040,
"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": 11.0443,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8235,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1856,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9728,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8129,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7038,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5988,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5319,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4434,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4027,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3513,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3122,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2479,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.211,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1762,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1295,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1143,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0799,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0411,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0213,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983231380739706e-05,
"loss": 5.0037,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9739,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9551,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9232,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.917,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8965,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8739,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8545,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8295,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8209,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8045,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7979,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7818,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7678,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7587,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7495,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7372,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7059,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7073,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6806,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6867,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6658,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 4.6696,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6485,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6466,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.636,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.629,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6184,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5929,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.6007,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6025,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5967,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5745,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 4.5631,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5651,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5514,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5668,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5275,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5443,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 4.5337,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 4.5146,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 4.5243,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5097,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.4994,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 4.494,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 4.5059,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4841,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4807,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 4.4712,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 4.4657,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4734,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4796,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.454,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4656,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4677,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4514,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4376,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4421,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4377,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4258,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.422,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4303,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4305,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4146,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3932,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4054,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4099,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.397,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.4028,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3841,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3836,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3774,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3772,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3816,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3699,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.386,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.37,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3526,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3557,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3626,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3539,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3516,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3512,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3396,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3418,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3208,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.3274,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3316,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3257,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3213,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3293,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3046,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3153,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3075,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.313,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3215,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3101,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3035,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2957,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.3031,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2961,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2945,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2861,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2845,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2854,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2746,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2805,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2776,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2723,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2648,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2806,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2829,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2695,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2591,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2659,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.2668,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.265,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2616,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2623,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2565,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2544,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2475,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2501,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2428,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2379,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2485,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2335,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.244,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.232,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.2265,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.199948310852051,
"eval_runtime": 463.9943,
"eval_samples_per_second": 822.404,
"eval_steps_per_second": 25.701,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.2192,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.2179,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2312,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2208,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2245,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.2138,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2107,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2019,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2165,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2092,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2194,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2023,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.1994,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1934,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1901,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1874,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1952,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1826,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1819,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.2017,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1871,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1891,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1763,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1897,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1742,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.175,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1738,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1652,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1607,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1618,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1691,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1689,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1619,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1685,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.165,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1635,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1505,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1532,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1397,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1531,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.1377,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1512,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1394,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1407,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.143,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.139,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.135,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1233,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1282,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1395,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1349,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1261,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1165,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1263,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1137,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1359,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1081,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1277,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1204,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1059,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.118,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.1124,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.1026,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.1043,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.1184,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.1057,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.1028,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818093729997386e-05,
"loss": 4.0981,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.0969,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1054,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1183,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147409888735514e-05,
"loss": 4.0989,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139023941224994e-05,
"loss": 4.1126,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1125,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.101,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.0918,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810549652998664e-05,
"loss": 4.1031,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.101,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.0917,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0928,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.0972,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.1035,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0927,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.0772,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0854,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.0909,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0871,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0913,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004930675075325e-05,
"loss": 4.0803,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996544727564805e-05,
"loss": 4.0757,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988158780054285e-05,
"loss": 4.074,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979772832543765e-05,
"loss": 4.0797,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971386885033245e-05,
"loss": 4.0807,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963000937522725e-05,
"loss": 4.077,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795463136881594e-05,
"loss": 4.0955,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0819,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0641,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.0737,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.0758,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791270163126334e-05,
"loss": 4.0761,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790431568375282e-05,
"loss": 4.073,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.78959297362423e-05,
"loss": 4.0711,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.0637,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787917422002499e-05,
"loss": 4.0735,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787078827251447e-05,
"loss": 4.0482,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.0628,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854032756297166e-05,
"loss": 4.0625,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845646808786646e-05,
"loss": 4.0634,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0535,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.066,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0509,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.0555,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803733450037775e-05,
"loss": 4.0567,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779534750252725e-05,
"loss": 4.0564,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778696155501673e-05,
"loss": 4.0711,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777857560750621e-05,
"loss": 4.0615,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0567,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0504,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0534,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.053,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.0485,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.0468,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.045,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.0494,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770315121632272e-05,
"loss": 4.0369,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.0451,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768637932130168e-05,
"loss": 4.0434,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0422,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0326,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0539,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765285191006334e-05,
"loss": 4.0566,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764446596255282e-05,
"loss": 4.0415,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76360800150423e-05,
"loss": 4.0333,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762769406753178e-05,
"loss": 4.0421,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761930812002126e-05,
"loss": 4.0438,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610938551314466e-05,
"loss": 4.0453,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602552603803946e-05,
"loss": 4.0403,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594166656293426e-05,
"loss": 4.0422,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585780708782906e-05,
"loss": 4.0361,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577411140076115e-05,
"loss": 4.0414,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569025192565595e-05,
"loss": 4.031,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560639245055075e-05,
"loss": 4.0382,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.0344,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0226,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753549778132725e-05,
"loss": 4.0398,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752711183381673e-05,
"loss": 4.027,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751872588630621e-05,
"loss": 4.0354,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751033993879569e-05,
"loss": 4.0235,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750195399128517e-05,
"loss": 4.0215,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.029198169708252,
"eval_runtime": 309.4125,
"eval_samples_per_second": 1233.276,
"eval_steps_per_second": 38.541,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749356804377465e-05,
"loss": 4.0196,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748518209626413e-05,
"loss": 4.0113,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747679614875361e-05,
"loss": 4.0325,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468410201243084e-05,
"loss": 4.022,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460024253732563e-05,
"loss": 4.0294,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451638306222043e-05,
"loss": 4.0134,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744325235871152e-05,
"loss": 4.0174,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434866411201e-05,
"loss": 4.0037,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742648046369049e-05,
"loss": 4.0199,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741809451617997e-05,
"loss": 4.0229,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740970856866945e-05,
"loss": 4.0234,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740133899996266e-05,
"loss": 4.0143,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739296943125587e-05,
"loss": 4.0081,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738458348374535e-05,
"loss": 4.0067,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737619753623483e-05,
"loss": 4.0021,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736781158872431e-05,
"loss": 4.0024,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735942564121379e-05,
"loss": 4.0071,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735103969370327e-05,
"loss": 3.9982,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734265374619275e-05,
"loss": 4.0008,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733426779868223e-05,
"loss": 4.0206,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732588185117171e-05,
"loss": 4.0064,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731749590366119e-05,
"loss": 4.0109,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309109956150674e-05,
"loss": 3.9984,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300740387443884e-05,
"loss": 4.0136,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729237081873709e-05,
"loss": 3.9895,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728398487122657e-05,
"loss": 4.0029,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727559892371605e-05,
"loss": 3.9986,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726721297620553e-05,
"loss": 3.9959,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725882702869501e-05,
"loss": 3.983,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725044108118449e-05,
"loss": 3.99,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724205513367397e-05,
"loss": 3.9978,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233669186163446e-05,
"loss": 4.0001,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.72253159962604e-05,
"loss": 3.9956,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721693004874988e-05,
"loss": 3.9961,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720854410123936e-05,
"loss": 3.9948,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720015815372884e-05,
"loss": 3.9958,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719177220621832e-05,
"loss": 3.9861,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833862587078e-05,
"loss": 3.9878,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717500031119727e-05,
"loss": 3.9763,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166630742490486e-05,
"loss": 3.9918,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158244794979966e-05,
"loss": 3.978,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149858847469446e-05,
"loss": 3.9907,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714147289995892e-05,
"loss": 3.9815,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133103331252135e-05,
"loss": 3.9768,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124717383741615e-05,
"loss": 3.9899,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116331436231095e-05,
"loss": 3.9768,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107945488720575e-05,
"loss": 3.9797,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709957592001379e-05,
"loss": 3.9627,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709118997250327e-05,
"loss": 3.9755,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082804024992744e-05,
"loss": 3.9828,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074418077482224e-05,
"loss": 3.9805,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706606488757917e-05,
"loss": 3.977,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705767894006865e-05,
"loss": 3.9612,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704929299255813e-05,
"loss": 3.9749,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704090704504761e-05,
"loss": 3.9611,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703252109753709e-05,
"loss": 3.9834,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702413515002657e-05,
"loss": 3.9602,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701574920251605e-05,
"loss": 3.9773,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700736325500553e-05,
"loss": 3.9753,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9545,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.965,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9697,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973852222570914e-05,
"loss": 3.9564,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965466275060394e-05,
"loss": 3.9596,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9709,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9665,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9543,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693193886382204e-05,
"loss": 3.9588,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692355291631152e-05,
"loss": 3.9512,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691518334760474e-05,
"loss": 3.9627,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690679740009422e-05,
"loss": 3.9766,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689841145258369e-05,
"loss": 3.9604,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689002550507317e-05,
"loss": 3.9735,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688163955756265e-05,
"loss": 3.9698,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687325361005213e-05,
"loss": 3.9643,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686488404134534e-05,
"loss": 3.9506,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685649809383482e-05,
"loss": 3.9689,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.68481121463243e-05,
"loss": 3.9609,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683972619881378e-05,
"loss": 3.9582,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683134025130326e-05,
"loss": 3.9554,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682295430379274e-05,
"loss": 3.9613,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681456835628222e-05,
"loss": 3.9726,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806198787575436e-05,
"loss": 3.9557,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797812840064916e-05,
"loss": 3.942,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789426892554396e-05,
"loss": 3.9487,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781040945043876e-05,
"loss": 3.9584,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772654997533356e-05,
"loss": 3.9573,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764269050022836e-05,
"loss": 3.9596,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755899481316045e-05,
"loss": 3.9447,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747513533805525e-05,
"loss": 3.9496,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739127586295005e-05,
"loss": 3.9385,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730741638784485e-05,
"loss": 3.9477,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722372070077694e-05,
"loss": 3.9522,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713986122567174e-05,
"loss": 3.9515,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670560017505666e-05,
"loss": 3.9702,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669721422754614e-05,
"loss": 3.9484,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668882828003562e-05,
"loss": 3.9403,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.66804423325251e-05,
"loss": 3.946,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667205638501458e-05,
"loss": 3.9463,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663670437504054e-05,
"loss": 3.9536,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665530086879727e-05,
"loss": 3.9483,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664693130009048e-05,
"loss": 3.9423,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.9412,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9492,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9247,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.66133875100484e-05,
"loss": 3.9407,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6605017941341614e-05,
"loss": 3.9379,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596631993831094e-05,
"loss": 3.9416,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588246046320574e-05,
"loss": 3.9333,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579860098810054e-05,
"loss": 3.9434,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657147415129953e-05,
"loss": 3.9305,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656308820378901e-05,
"loss": 3.9321,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655471863508222e-05,
"loss": 3.9412,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.65463326875717e-05,
"loss": 3.9329,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537946740061176e-05,
"loss": 3.9519,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529560792550656e-05,
"loss": 3.944,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652119122384387e-05,
"loss": 3.9384,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651280527633335e-05,
"loss": 3.9302,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650441932882283e-05,
"loss": 3.9335,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649603338131231e-05,
"loss": 3.9361,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648766381260553e-05,
"loss": 3.9341,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479277865095e-05,
"loss": 3.931,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647089191758448e-05,
"loss": 3.9238,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646250597007396e-05,
"loss": 3.9347,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645412002256344e-05,
"loss": 3.9207,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9298,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9279,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642897855883561e-05,
"loss": 3.9261,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642059261132509e-05,
"loss": 3.9176,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9417,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9424,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395451147597266e-05,
"loss": 3.9329,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387065200086746e-05,
"loss": 3.9147,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378679252576226e-05,
"loss": 3.9312,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9286,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361923736358915e-05,
"loss": 3.9354,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353537788848395e-05,
"loss": 3.928,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345151841337874e-05,
"loss": 3.9269,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336765893827354e-05,
"loss": 3.9252,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9319,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.9246,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311624430099523e-05,
"loss": 3.9261,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303238482589003e-05,
"loss": 3.9257,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9133,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9289,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627809701886118e-05,
"loss": 3.9251,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626971107135066e-05,
"loss": 3.9205,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626132512384014e-05,
"loss": 3.916,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625293917632962e-05,
"loss": 3.9133,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.954420804977417,
"eval_runtime": 311.7206,
"eval_samples_per_second": 1224.144,
"eval_steps_per_second": 38.255,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624456960762283e-05,
"loss": 3.9169,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623618366011231e-05,
"loss": 3.9074,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622779771260179e-05,
"loss": 3.9231,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621941176509127e-05,
"loss": 3.9158,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621104219638448e-05,
"loss": 3.926,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620265624887396e-05,
"loss": 3.908,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619427030136344e-05,
"loss": 3.9129,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185884353852924e-05,
"loss": 3.8996,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177498406342404e-05,
"loss": 3.9162,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616912883763561e-05,
"loss": 3.9163,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616074289012509e-05,
"loss": 3.9183,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615235694261457e-05,
"loss": 3.9102,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614398737390778e-05,
"loss": 3.9063,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613560142639726e-05,
"loss": 3.9061,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612721547888674e-05,
"loss": 3.8998,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611882953137622e-05,
"loss": 3.9022,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.61104435838657e-05,
"loss": 3.9066,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610205763635518e-05,
"loss": 3.8993,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609367168884466e-05,
"loss": 3.8994,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608528574133414e-05,
"loss": 3.9247,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607689979382362e-05,
"loss": 3.9064,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606853022511684e-05,
"loss": 3.9069,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606014427760631e-05,
"loss": 3.9029,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605175833009579e-05,
"loss": 3.9092,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604337238258527e-05,
"loss": 3.8936,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603498643507475e-05,
"loss": 3.9097,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602661686636796e-05,
"loss": 3.8984,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601823091885744e-05,
"loss": 3.8963,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600984497134692e-05,
"loss": 3.8863,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.60014590238364e-05,
"loss": 3.8949,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5993089455129615e-05,
"loss": 3.8994,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984703507619095e-05,
"loss": 3.9043,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.5976317560108575e-05,
"loss": 3.9037,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967931612598055e-05,
"loss": 3.9006,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959562043891264e-05,
"loss": 3.8936,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5951176096380744e-05,
"loss": 3.9039,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942790148870224e-05,
"loss": 3.8883,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934404201359704e-05,
"loss": 3.897,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592603463265291e-05,
"loss": 3.8809,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591764868514239e-05,
"loss": 3.8958,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590926273763187e-05,
"loss": 3.8847,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590087679012135e-05,
"loss": 3.8971,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589250722141457e-05,
"loss": 3.8907,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588412127390405e-05,
"loss": 3.8826,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587573532639353e-05,
"loss": 3.8965,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586734937888301e-05,
"loss": 3.8863,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585896343137249e-05,
"loss": 3.8853,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.58505938626657e-05,
"loss": 3.873,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584220791515518e-05,
"loss": 3.8815,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583382196764466e-05,
"loss": 3.889,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582543602013414e-05,
"loss": 3.8891,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581706645142735e-05,
"loss": 3.8853,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580868050391683e-05,
"loss": 3.8714,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580029455640631e-05,
"loss": 3.8843,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579190860889579e-05,
"loss": 3.8708,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783539040189e-05,
"loss": 3.8899,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577515309267848e-05,
"loss": 3.8774,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576676714516796e-05,
"loss": 3.8844,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575838119765744e-05,
"loss": 3.8878,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.575001162895065e-05,
"loss": 3.8705,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574162568144013e-05,
"loss": 3.874,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573323973392961e-05,
"loss": 3.8831,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572485378641909e-05,
"loss": 3.8678,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.57164842177123e-05,
"loss": 3.8761,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570809827020178e-05,
"loss": 3.8792,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569971232269126e-05,
"loss": 3.8822,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569132637518074e-05,
"loss": 3.8671,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682956806473956e-05,
"loss": 3.8738,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674570858963436e-05,
"loss": 3.8636,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666184911452916e-05,
"loss": 3.8745,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657798963942396e-05,
"loss": 3.8863,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649413016431876e-05,
"loss": 3.8766,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641043447725085e-05,
"loss": 3.8864,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632657500214565e-05,
"loss": 3.8844,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624271552704045e-05,
"loss": 3.8838,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615885605193525e-05,
"loss": 3.8622,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.5607516036486734e-05,
"loss": 3.8817,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599130088976214e-05,
"loss": 3.8809,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590744141465694e-05,
"loss": 3.8693,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582358193955174e-05,
"loss": 3.8749,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557398862524839e-05,
"loss": 3.8765,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556560267773787e-05,
"loss": 3.8897,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555721673022735e-05,
"loss": 3.8724,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554883078271683e-05,
"loss": 3.8575,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554046121401004e-05,
"loss": 3.8694,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553207526649952e-05,
"loss": 3.8721,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523689318989e-05,
"loss": 3.8734,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551530337147848e-05,
"loss": 3.8749,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550693380277169e-05,
"loss": 3.8666,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549854785526117e-05,
"loss": 3.8689,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549016190775065e-05,
"loss": 3.8575,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548177596024013e-05,
"loss": 3.8635,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547339001272961e-05,
"loss": 3.8669,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5465020444022823e-05,
"loss": 3.876,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566344965123e-05,
"loss": 3.8902,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544824854900178e-05,
"loss": 3.8655,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543986260149126e-05,
"loss": 3.856,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543149303278447e-05,
"loss": 3.8669,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542310708527395e-05,
"loss": 3.8646,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541472113776343e-05,
"loss": 3.8746,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540633519025291e-05,
"loss": 3.865,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539796562154612e-05,
"loss": 3.8642,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.53895796740356e-05,
"loss": 3.8622,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538119372652508e-05,
"loss": 3.8717,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537280777901456e-05,
"loss": 3.8461,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536443821030778e-05,
"loss": 3.8607,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535605226279726e-05,
"loss": 3.8549,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534766631528674e-05,
"loss": 3.8676,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533928036777621e-05,
"loss": 3.8522,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533089442026569e-05,
"loss": 3.8623,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322524851558906e-05,
"loss": 3.852,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314138904048386e-05,
"loss": 3.8564,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530575295653786e-05,
"loss": 3.8614,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529736700902734e-05,
"loss": 3.8594,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5288997440320555e-05,
"loss": 3.8708,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.5280611492810035e-05,
"loss": 3.8686,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527224192410325e-05,
"loss": 3.8609,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526385597659273e-05,
"loss": 3.8542,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525547002908221e-05,
"loss": 3.8559,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5247084081571684e-05,
"loss": 3.861,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238698134061164e-05,
"loss": 3.8521,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230312186550644e-05,
"loss": 3.8566,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221926239040124e-05,
"loss": 3.8544,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213540291529604e-05,
"loss": 3.8537,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520517072282281e-05,
"loss": 3.8497,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519678477531229e-05,
"loss": 3.8529,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518839882780177e-05,
"loss": 3.8507,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.518001288029125e-05,
"loss": 3.8546,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517164331158447e-05,
"loss": 3.8407,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516325736407395e-05,
"loss": 3.868,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515487141656343e-05,
"loss": 3.8632,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514648546905291e-05,
"loss": 3.8642,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513811590034612e-05,
"loss": 3.8383,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.51297299528356e-05,
"loss": 3.8569,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512134400532508e-05,
"loss": 3.8586,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511295805781456e-05,
"loss": 3.8574,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104588489107766e-05,
"loss": 3.8562,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096202541597246e-05,
"loss": 3.8532,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087816594086726e-05,
"loss": 3.8527,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079430646576206e-05,
"loss": 3.8597,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507104469906569e-05,
"loss": 3.8518,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.50626751303589e-05,
"loss": 3.8522,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505428918284838e-05,
"loss": 3.8523,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504590323533786e-05,
"loss": 3.8403,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503751728782734e-05,
"loss": 3.8584,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502914771912055e-05,
"loss": 3.8539,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502076177161003e-05,
"loss": 3.851,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501237582409951e-05,
"loss": 3.8413,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500398987658899e-05,
"loss": 3.8411,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9124677181243896,
"eval_runtime": 305.0369,
"eval_samples_per_second": 1250.967,
"eval_steps_per_second": 39.094,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499560392907847e-05,
"loss": 3.843,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498721798156795e-05,
"loss": 3.8357,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497883203405743e-05,
"loss": 3.8483,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497044608654691e-05,
"loss": 3.846,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496206013903639e-05,
"loss": 3.8601,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495367419152587e-05,
"loss": 3.8359,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494528824401535e-05,
"loss": 3.8404,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493690229650483e-05,
"loss": 3.828,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928532727798047e-05,
"loss": 3.848,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492014678028752e-05,
"loss": 3.8467,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911760832777e-05,
"loss": 3.8435,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490337488526648e-05,
"loss": 3.8439,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489500531655969e-05,
"loss": 3.8329,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488661936904917e-05,
"loss": 3.8413,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487823342153865e-05,
"loss": 3.8267,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486984747402813e-05,
"loss": 3.8364,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486146152651761e-05,
"loss": 3.8344,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853075579007095e-05,
"loss": 3.8318,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844689631496575e-05,
"loss": 3.8355,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836303683986055e-05,
"loss": 3.8526,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827934115279264e-05,
"loss": 3.8335,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.4819548167768744e-05,
"loss": 3.8399,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.4811162220258224e-05,
"loss": 3.8331,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802776272747704e-05,
"loss": 3.8419,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479440670404091e-05,
"loss": 3.8287,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478602075653039e-05,
"loss": 3.8415,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477763480901987e-05,
"loss": 3.8311,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476924886150935e-05,
"loss": 3.8287,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476087929280256e-05,
"loss": 3.8214,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475249334529205e-05,
"loss": 3.826,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474410739778153e-05,
"loss": 3.8311,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473572145027101e-05,
"loss": 3.8372,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472735188156422e-05,
"loss": 3.8376,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.47189659340537e-05,
"loss": 3.8332,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471057998654318e-05,
"loss": 3.8277,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470219403903266e-05,
"loss": 3.8387,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469382447032587e-05,
"loss": 3.8292,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468543852281535e-05,
"loss": 3.8282,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467705257530483e-05,
"loss": 3.8131,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466866662779431e-05,
"loss": 3.8272,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660297059087516e-05,
"loss": 3.8225,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651911111577e-05,
"loss": 3.8341,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464352516406648e-05,
"loss": 3.8263,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463513921655596e-05,
"loss": 3.8163,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462676964784917e-05,
"loss": 3.834,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461838370033865e-05,
"loss": 3.8237,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460999775282813e-05,
"loss": 3.8196,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460161180531761e-05,
"loss": 3.8111,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459324223661082e-05,
"loss": 3.8131,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.45848562891003e-05,
"loss": 3.8237,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457647034158978e-05,
"loss": 3.8246,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456808439407926e-05,
"loss": 3.8197,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455971482537247e-05,
"loss": 3.8123,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551328877861956e-05,
"loss": 3.8241,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542942930351436e-05,
"loss": 3.8072,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534556982840916e-05,
"loss": 3.8236,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526187414134125e-05,
"loss": 3.8109,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517801466623605e-05,
"loss": 3.8236,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509415519113085e-05,
"loss": 3.82,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4501029571602565e-05,
"loss": 3.8146,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492660002895774e-05,
"loss": 3.8098,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484274055385254e-05,
"loss": 3.8207,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475888107874734e-05,
"loss": 3.8054,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.4467502160364214e-05,
"loss": 3.8128,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445913259165742e-05,
"loss": 3.8204,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445074664414691e-05,
"loss": 3.82,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444236069663639e-05,
"loss": 3.807,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443397474912587e-05,
"loss": 3.8091,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442560518041908e-05,
"loss": 3.8068,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441721923290856e-05,
"loss": 3.8083,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440883328539804e-05,
"loss": 3.8227,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440044733788752e-05,
"loss": 3.8166,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439207776918073e-05,
"loss": 3.8276,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438369182167021e-05,
"loss": 3.8237,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437530587415969e-05,
"loss": 3.8241,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436691992664917e-05,
"loss": 3.8058,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435855035794238e-05,
"loss": 3.8157,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4350164410431864e-05,
"loss": 3.824,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341778462921344e-05,
"loss": 3.8088,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333392515410824e-05,
"loss": 3.812,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432502294670403e-05,
"loss": 3.8151,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431663699919351e-05,
"loss": 3.8301,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430825105168299e-05,
"loss": 3.8119,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429986510417247e-05,
"loss": 3.7964,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429149553546568e-05,
"loss": 3.8089,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428310958795516e-05,
"loss": 3.8126,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427472364044464e-05,
"loss": 3.8161,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426633769293412e-05,
"loss": 3.8147,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425796812422733e-05,
"loss": 3.8048,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424958217671682e-05,
"loss": 3.807,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.42411962292063e-05,
"loss": 3.8056,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423281028169577e-05,
"loss": 3.8009,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224440712988986e-05,
"loss": 3.8099,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216054765478466e-05,
"loss": 3.8151,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207668817967946e-05,
"loss": 3.8293,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419928287045742e-05,
"loss": 3.8146,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190913301750635e-05,
"loss": 3.7945,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182527354240115e-05,
"loss": 3.808,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174141406729595e-05,
"loss": 3.8034,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416575545921907e-05,
"loss": 3.8151,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157385890512284e-05,
"loss": 3.8113,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414899994300177e-05,
"loss": 3.8067,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140613995491244e-05,
"loss": 3.8026,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132228047980724e-05,
"loss": 3.8117,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412385847927394e-05,
"loss": 3.791,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411547253176342e-05,
"loss": 3.8048,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410708658425289e-05,
"loss": 3.795,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409871701554611e-05,
"loss": 3.8121,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409033106803559e-05,
"loss": 3.7979,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408194512052507e-05,
"loss": 3.8022,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407355917301454e-05,
"loss": 3.7945,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406518960430776e-05,
"loss": 3.8018,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405680365679724e-05,
"loss": 3.8047,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404841770928672e-05,
"loss": 3.8022,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40400317617762e-05,
"loss": 3.8135,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031662193069414e-05,
"loss": 3.8133,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402329262436262e-05,
"loss": 3.8039,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.40149066768521e-05,
"loss": 3.7981,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400652072934158e-05,
"loss": 3.7988,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399813478183106e-05,
"loss": 3.8082,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398974883432054e-05,
"loss": 3.7903,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.3981362886810016e-05,
"loss": 3.8046,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.3972976939299496e-05,
"loss": 3.7922,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.3964590991788976e-05,
"loss": 3.8006,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395622142308219e-05,
"loss": 3.7965,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394783547557167e-05,
"loss": 3.7965,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393944952806115e-05,
"loss": 3.7899,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393106358055063e-05,
"loss": 3.8024,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392269401184384e-05,
"loss": 3.7882,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391430806433332e-05,
"loss": 3.8116,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.39059221168228e-05,
"loss": 3.804,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389753616931228e-05,
"loss": 3.8133,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388916660060549e-05,
"loss": 3.7804,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388078065309497e-05,
"loss": 3.8036,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387239470558445e-05,
"loss": 3.803,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386400875807393e-05,
"loss": 3.8023,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855639189367145e-05,
"loss": 3.8013,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847253241856625e-05,
"loss": 3.8021,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838867294346105e-05,
"loss": 3.797,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830481346835585e-05,
"loss": 3.8055,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3822111778128794e-05,
"loss": 3.7907,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813725830618274e-05,
"loss": 3.7978,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805339883107754e-05,
"loss": 3.7962,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796953935597234e-05,
"loss": 3.7883,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378858436689044e-05,
"loss": 3.7984,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378019841937992e-05,
"loss": 3.8039,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.37718124718694e-05,
"loss": 3.7957,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376342652435888e-05,
"loss": 3.7828,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550569556521e-05,
"loss": 3.7911,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.8867132663726807,
"eval_runtime": 304.4412,
"eval_samples_per_second": 1253.414,
"eval_steps_per_second": 39.17,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374667100814158e-05,
"loss": 3.7984,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373828506063106e-05,
"loss": 3.7819,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372989911312054e-05,
"loss": 3.7941,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372152954441375e-05,
"loss": 3.7971,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371314359690323e-05,
"loss": 3.8031,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370475764939271e-05,
"loss": 3.788,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369637170188219e-05,
"loss": 3.7857,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.36880021331754e-05,
"loss": 3.775,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367961618566488e-05,
"loss": 3.7925,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367123023815436e-05,
"loss": 3.7967,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366284429064384e-05,
"loss": 3.7885,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365447472193705e-05,
"loss": 3.7922,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364610515323026e-05,
"loss": 3.7811,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363771920571974e-05,
"loss": 3.7889,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362933325820922e-05,
"loss": 3.777,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.36209473106987e-05,
"loss": 3.7823,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361256136318818e-05,
"loss": 3.7784,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360417541567766e-05,
"loss": 3.7857,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359578946816714e-05,
"loss": 3.7793,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358740352065662e-05,
"loss": 3.7996,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357903395194983e-05,
"loss": 3.786,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357064800443931e-05,
"loss": 3.7946,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356226205692879e-05,
"loss": 3.7799,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355387610941827e-05,
"loss": 3.7897,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.3545506540711486e-05,
"loss": 3.7754,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.3537120593200966e-05,
"loss": 3.79,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.3528734645690446e-05,
"loss": 3.7825,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.3520348698179926e-05,
"loss": 3.7721,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511979129473135e-05,
"loss": 3.7709,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503593181962615e-05,
"loss": 3.7738,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3495207234452095e-05,
"loss": 3.7807,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486837665745304e-05,
"loss": 3.7842,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.3478451718234784e-05,
"loss": 3.7866,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3470065770724264e-05,
"loss": 3.7859,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.3461679823213744e-05,
"loss": 3.7768,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345331025450696e-05,
"loss": 3.7867,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344492430699644e-05,
"loss": 3.7793,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343653835948592e-05,
"loss": 3.7781,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.34281524119754e-05,
"loss": 3.7625,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341978284326861e-05,
"loss": 3.7777,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341139689575809e-05,
"loss": 3.7723,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340301094824757e-05,
"loss": 3.7847,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339462500073705e-05,
"loss": 3.777,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338625543203026e-05,
"loss": 3.7685,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337786948451974e-05,
"loss": 3.7847,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336948353700922e-05,
"loss": 3.7698,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.33610975894987e-05,
"loss": 3.7723,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352728020791914e-05,
"loss": 3.7638,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.3344342073281393e-05,
"loss": 3.7625,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.3335956125770873e-05,
"loss": 3.7752,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.3327570178260353e-05,
"loss": 3.7763,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331920060955356e-05,
"loss": 3.7685,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331081466204304e-05,
"loss": 3.7648,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330244509333625e-05,
"loss": 3.7757,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329405914582573e-05,
"loss": 3.7546,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328567319831521e-05,
"loss": 3.7773,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327728725080469e-05,
"loss": 3.7634,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326890130329417e-05,
"loss": 3.7728,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326051535578365e-05,
"loss": 3.7704,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325212940827313e-05,
"loss": 3.7669,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324374346076261e-05,
"loss": 3.7609,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323537389205583e-05,
"loss": 3.7703,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322698794454531e-05,
"loss": 3.7634,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321860199703479e-05,
"loss": 3.7612,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321021604952427e-05,
"loss": 3.7711,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.3201846480817476e-05,
"loss": 3.7702,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.3193460533306956e-05,
"loss": 3.7576,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3185074585796436e-05,
"loss": 3.7664,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.3176688638285916e-05,
"loss": 3.755,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3168319069579125e-05,
"loss": 3.7602,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.3159933122068605e-05,
"loss": 3.7761,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.3151547174558085e-05,
"loss": 3.7713,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.3143161227047565e-05,
"loss": 3.7756,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313479165834078e-05,
"loss": 3.7724,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312640571083026e-05,
"loss": 3.7815,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311801976331974e-05,
"loss": 3.761,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.3109633815809214e-05,
"loss": 3.7653,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310126424710243e-05,
"loss": 3.7756,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309287829959191e-05,
"loss": 3.7585,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308449235208139e-05,
"loss": 3.7686,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307610640457086e-05,
"loss": 3.7714,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306773683586408e-05,
"loss": 3.7768,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305935088835356e-05,
"loss": 3.7649,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305096494084304e-05,
"loss": 3.7527,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.304257899333252e-05,
"loss": 3.7605,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3034209424625734e-05,
"loss": 3.7648,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025823477115214e-05,
"loss": 3.7688,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301743752960469e-05,
"loss": 3.7677,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300905158209417e-05,
"loss": 3.762,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000682013387383e-05,
"loss": 3.7645,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299229606587686e-05,
"loss": 3.7549,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983910118366337e-05,
"loss": 3.7536,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.2975524170855817e-05,
"loss": 3.7606,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296715460214903e-05,
"loss": 3.7701,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295876865463851e-05,
"loss": 3.7849,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295038270712799e-05,
"loss": 3.7693,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294199675961747e-05,
"loss": 3.7474,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293362719091069e-05,
"loss": 3.7655,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292524124340016e-05,
"loss": 3.7578,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291685529588964e-05,
"loss": 3.7696,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290846934837912e-05,
"loss": 3.761,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.290009977967234e-05,
"loss": 3.7614,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289171383216181e-05,
"loss": 3.7587,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288332788465129e-05,
"loss": 3.7629,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287494193714077e-05,
"loss": 3.7507,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286657236843398e-05,
"loss": 3.7593,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.2858186420923466e-05,
"loss": 3.7475,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849800473412946e-05,
"loss": 3.7698,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284143090470616e-05,
"loss": 3.7515,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2833044957195635e-05,
"loss": 3.755,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.2824659009685115e-05,
"loss": 3.7464,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.2816273062174595e-05,
"loss": 3.7609,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2807887114664075e-05,
"loss": 3.759,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.2799501167153555e-05,
"loss": 3.7571,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2791115219643035e-05,
"loss": 3.7686,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.2782729272132515e-05,
"loss": 3.7676,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277437608222945e-05,
"loss": 3.762,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276599013471893e-05,
"loss": 3.7562,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275760418720842e-05,
"loss": 3.7509,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.27492182396979e-05,
"loss": 3.7645,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274083229218738e-05,
"loss": 3.7486,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273244634467686e-05,
"loss": 3.7588,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272406039716634e-05,
"loss": 3.7454,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271567444965582e-05,
"loss": 3.76,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270730488094903e-05,
"loss": 3.746,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269891893343851e-05,
"loss": 3.7544,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269053298592799e-05,
"loss": 3.7509,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268214703841747e-05,
"loss": 3.7531,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267377746971068e-05,
"loss": 3.7483,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266539152220016e-05,
"loss": 3.7645,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.265700557468964e-05,
"loss": 3.7624,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.264861962717912e-05,
"loss": 3.7653,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.264025005847233e-05,
"loss": 3.7393,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.263186411096181e-05,
"loss": 3.7606,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262347816345129e-05,
"loss": 3.7574,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261509221594077e-05,
"loss": 3.7605,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260672264723398e-05,
"loss": 3.7548,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259833669972346e-05,
"loss": 3.7594,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.258995075221294e-05,
"loss": 3.7537,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258156480470242e-05,
"loss": 3.7638,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257319523599563e-05,
"loss": 3.7463,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256480928848511e-05,
"loss": 3.7586,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255642334097459e-05,
"loss": 3.7529,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254803739346407e-05,
"loss": 3.7483,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253966782475729e-05,
"loss": 3.7554,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253128187724677e-05,
"loss": 3.7549,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252289592973625e-05,
"loss": 3.7585,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251450998222573e-05,
"loss": 3.7376,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.2506140413518936e-05,
"loss": 3.7507,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.8703999519348145,
"eval_runtime": 303.1842,
"eval_samples_per_second": 1258.611,
"eval_steps_per_second": 39.333,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.2497754466008416e-05,
"loss": 3.7501,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.2489368518497896e-05,
"loss": 3.7374,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.2480982570987376e-05,
"loss": 3.751,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.2472596623476856e-05,
"loss": 3.7542,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.2464210675966336e-05,
"loss": 3.7623,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.2455824728455816e-05,
"loss": 3.7426,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.2447438780945296e-05,
"loss": 3.741,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.2439052833434776e-05,
"loss": 3.7403,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243068326472799e-05,
"loss": 3.7451,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242229731721747e-05,
"loss": 3.7544,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.2413911369706945e-05,
"loss": 3.7463,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.2405525422196424e-05,
"loss": 3.7504,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239717223229337e-05,
"loss": 3.7433,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238878628478285e-05,
"loss": 3.7431,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238040033727233e-05,
"loss": 3.739,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237201438976181e-05,
"loss": 3.7411,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236362844225129e-05,
"loss": 3.7376,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235524249474076e-05,
"loss": 3.7396,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234685654723025e-05,
"loss": 3.7405,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233847059971973e-05,
"loss": 3.7566,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.2330101031012945e-05,
"loss": 3.7436,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232171508350242e-05,
"loss": 3.7519,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.23133291359919e-05,
"loss": 3.7367,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230494318848138e-05,
"loss": 3.7504,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.229657361977459e-05,
"loss": 3.7331,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.228818767226407e-05,
"loss": 3.7476,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.227980172475355e-05,
"loss": 3.7391,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227141577724303e-05,
"loss": 3.7314,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226306258733997e-05,
"loss": 3.735,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.225467663982945e-05,
"loss": 3.7336,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.224629069231893e-05,
"loss": 3.74,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223790474480841e-05,
"loss": 3.7427,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222951879729789e-05,
"loss": 3.7456,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222113284978737e-05,
"loss": 3.7484,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221274690227685e-05,
"loss": 3.7318,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220437733357006e-05,
"loss": 3.7472,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219599138605954e-05,
"loss": 3.7431,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218760543854902e-05,
"loss": 3.7328,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.21792194910385e-05,
"loss": 3.7243,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217084992233171e-05,
"loss": 3.7331,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216246397482119e-05,
"loss": 3.7365,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215407802731067e-05,
"loss": 3.7426,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214569207980015e-05,
"loss": 3.7353,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.2137322511093366e-05,
"loss": 3.7301,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.2128936563582846e-05,
"loss": 3.7482,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.2120550616072326e-05,
"loss": 3.7306,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.2112164668561806e-05,
"loss": 3.7324,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103795099855015e-05,
"loss": 3.7241,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.2095409152344495e-05,
"loss": 3.7206,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.2087023204833975e-05,
"loss": 3.7358,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.2078637257323454e-05,
"loss": 3.7367,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070251309812934e-05,
"loss": 3.7301,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061865362302414e-05,
"loss": 3.7228,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2053479414791894e-05,
"loss": 3.7387,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.2045093467281374e-05,
"loss": 3.7148,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203672389857459e-05,
"loss": 3.7364,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202833795106407e-05,
"loss": 3.7249,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201995200355355e-05,
"loss": 3.7292,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201156605604303e-05,
"loss": 3.7355,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200319648733624e-05,
"loss": 3.7254,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199481053982572e-05,
"loss": 3.7217,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.19864245923152e-05,
"loss": 3.7374,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197803864480468e-05,
"loss": 3.7209,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196966907609789e-05,
"loss": 3.724,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196128312858737e-05,
"loss": 3.7314,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195289718107685e-05,
"loss": 3.7311,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194451123356633e-05,
"loss": 3.7185,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.1936141664859544e-05,
"loss": 3.7266,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.1927755717349024e-05,
"loss": 3.7156,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.1919369769838504e-05,
"loss": 3.7219,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.1910983822327984e-05,
"loss": 3.7347,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.190261425362119e-05,
"loss": 3.7302,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.189422830611067e-05,
"loss": 3.7381,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.188584235860015e-05,
"loss": 3.732,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.187745641108963e-05,
"loss": 3.7465,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.186908684238284e-05,
"loss": 3.7207,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186070089487232e-05,
"loss": 3.7325,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.18523149473618e-05,
"loss": 3.7373,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.184394537865501e-05,
"loss": 3.7181,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.18355594311445e-05,
"loss": 3.7294,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182717348363398e-05,
"loss": 3.733,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181878753612346e-05,
"loss": 3.7391,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.1810417967416667e-05,
"loss": 3.7268,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.1802032019906146e-05,
"loss": 3.7164,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.1793646072395626e-05,
"loss": 3.7201,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.1785260124885106e-05,
"loss": 3.7255,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776890556178315e-05,
"loss": 3.7318,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.1768504608667795e-05,
"loss": 3.7295,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.1760118661157275e-05,
"loss": 3.7285,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.1751732713646755e-05,
"loss": 3.7175,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.1743363144939964e-05,
"loss": 3.719,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173497719742945e-05,
"loss": 3.7188,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172659124991893e-05,
"loss": 3.7224,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171820530240841e-05,
"loss": 3.7336,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170983573370162e-05,
"loss": 3.7434,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170146616499483e-05,
"loss": 3.7332,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169308021748431e-05,
"loss": 3.714,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168469426997379e-05,
"loss": 3.7238,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167630832246327e-05,
"loss": 3.7204,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166792237495275e-05,
"loss": 3.7316,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165953642744223e-05,
"loss": 3.7237,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165115047993171e-05,
"loss": 3.7268,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164278091122492e-05,
"loss": 3.7236,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1634394963714405e-05,
"loss": 3.72,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1626009016203885e-05,
"loss": 3.7162,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617623068693365e-05,
"loss": 3.7189,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1609253499986574e-05,
"loss": 3.7109,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1600867552476054e-05,
"loss": 3.7309,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159249798376926e-05,
"loss": 3.7164,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158411203625874e-05,
"loss": 3.7184,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157572608874822e-05,
"loss": 3.7134,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.15673401412377e-05,
"loss": 3.7196,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155895419372718e-05,
"loss": 3.7265,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155056824621666e-05,
"loss": 3.7187,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154218229870614e-05,
"loss": 3.7321,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153379635119562e-05,
"loss": 3.7268,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152544316129257e-05,
"loss": 3.7243,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151705721378205e-05,
"loss": 3.7233,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150867126627153e-05,
"loss": 3.7089,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150028531876101e-05,
"loss": 3.733,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149189937125049e-05,
"loss": 3.7176,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148351342373997e-05,
"loss": 3.7204,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147512747622944e-05,
"loss": 3.7107,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.146674152871892e-05,
"loss": 3.7204,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1458371960012136e-05,
"loss": 3.7122,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.144998601250161e-05,
"loss": 3.7172,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441600064991096e-05,
"loss": 3.7119,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1433214117480576e-05,
"loss": 3.7209,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.142484454877379e-05,
"loss": 3.7103,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1416474980067e-05,
"loss": 3.7292,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140808903255648e-05,
"loss": 3.7223,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139970308504596e-05,
"loss": 3.7318,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139131713753544e-05,
"loss": 3.7062,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.1382931190024914e-05,
"loss": 3.7253,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.1374545242514394e-05,
"loss": 3.7211,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.1366159295003874e-05,
"loss": 3.7234,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.1357773347493354e-05,
"loss": 3.722,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134940377878656e-05,
"loss": 3.723,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134101783127604e-05,
"loss": 3.7145,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133263188376553e-05,
"loss": 3.7335,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132424593625501e-05,
"loss": 3.7058,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131587636754822e-05,
"loss": 3.7221,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.13074904200377e-05,
"loss": 3.7163,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129910447252718e-05,
"loss": 3.714,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129071852501666e-05,
"loss": 3.7185,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128234895630987e-05,
"loss": 3.7189,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127396300879935e-05,
"loss": 3.7252,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126557706128883e-05,
"loss": 3.7008,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125719111377831e-05,
"loss": 3.7187,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.8599042892456055,
"eval_runtime": 304.0185,
"eval_samples_per_second": 1255.157,
"eval_steps_per_second": 39.225,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124882154507152e-05,
"loss": 3.7188,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.1240435597561e-05,
"loss": 3.7029,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.1232049650050484e-05,
"loss": 3.715,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.1223663702539964e-05,
"loss": 3.7163,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.121529413383317e-05,
"loss": 3.7272,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.120690818632265e-05,
"loss": 3.7122,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.119852223881213e-05,
"loss": 3.7049,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.119015267010534e-05,
"loss": 3.7069,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.118176672259482e-05,
"loss": 3.7127,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.11733807750843e-05,
"loss": 3.7181,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116499482757378e-05,
"loss": 3.7099,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.115660888006326e-05,
"loss": 3.714,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114823931135647e-05,
"loss": 3.7093,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113985336384595e-05,
"loss": 3.7095,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113146741633544e-05,
"loss": 3.7024,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112308146882492e-05,
"loss": 3.7033,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.11146955213144e-05,
"loss": 3.7057,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110630957380388e-05,
"loss": 3.7048,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109792362629336e-05,
"loss": 3.7074,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108953767878284e-05,
"loss": 3.7165,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.1081168110076046e-05,
"loss": 3.7127,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.1072782162565526e-05,
"loss": 3.7165,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.1064396215055006e-05,
"loss": 3.7051,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.1056010267544486e-05,
"loss": 3.7117,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.1047640698837695e-05,
"loss": 3.6987,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.1039254751327175e-05,
"loss": 3.7185,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.1030868803816655e-05,
"loss": 3.7014,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.1022482856306135e-05,
"loss": 3.7006,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101412966640308e-05,
"loss": 3.7013,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.100574371889256e-05,
"loss": 3.7013,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.099735777138204e-05,
"loss": 3.7016,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.098897182387152e-05,
"loss": 3.71,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.0980585876361e-05,
"loss": 3.7123,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.097219992885048e-05,
"loss": 3.7075,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096381398133996e-05,
"loss": 3.7024,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095542803382944e-05,
"loss": 3.7135,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094705846512265e-05,
"loss": 3.7097,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.093867251761213e-05,
"loss": 3.6951,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.093028657010161e-05,
"loss": 3.6924,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.0921917001394825e-05,
"loss": 3.6992,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.0913531053884305e-05,
"loss": 3.7029,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.0905145106373784e-05,
"loss": 3.7084,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.0896759158863264e-05,
"loss": 3.7026,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.0888389590156474e-05,
"loss": 3.6962,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.0880003642645953e-05,
"loss": 3.7113,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.0871617695135433e-05,
"loss": 3.7004,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.0863231747624913e-05,
"loss": 3.7002,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085486217891812e-05,
"loss": 3.6877,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.08464762314076e-05,
"loss": 3.6833,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.083809028389708e-05,
"loss": 3.7068,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082970433638656e-05,
"loss": 3.6997,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082131838887604e-05,
"loss": 3.7003,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081293244136552e-05,
"loss": 3.694,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080456287265874e-05,
"loss": 3.698,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079617692514822e-05,
"loss": 3.6834,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078779097763769e-05,
"loss": 3.7011,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077940503012717e-05,
"loss": 3.6933,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077101908261665e-05,
"loss": 3.6954,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.076263313510613e-05,
"loss": 3.707,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075424718759561e-05,
"loss": 3.6915,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.074586124008509e-05,
"loss": 3.6871,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.07374916713783e-05,
"loss": 3.7029,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.072910572386778e-05,
"loss": 3.6908,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.072071977635726e-05,
"loss": 3.6859,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071233382884675e-05,
"loss": 3.703,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.0703964260139956e-05,
"loss": 3.6988,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.0695578312629436e-05,
"loss": 3.6835,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.0687208743922645e-05,
"loss": 3.697,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.0678822796412125e-05,
"loss": 3.6833,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.0670436848901605e-05,
"loss": 3.6867,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.0662050901391085e-05,
"loss": 3.7021,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.0653664953880565e-05,
"loss": 3.6997,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.0645279006370045e-05,
"loss": 3.7024,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.0636909437663254e-05,
"loss": 3.6995,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.0628523490152734e-05,
"loss": 3.7149,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.0620137542642214e-05,
"loss": 3.6902,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.06117515951317e-05,
"loss": 3.6981,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060336564762118e-05,
"loss": 3.7059,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.059497970011066e-05,
"loss": 3.6852,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.058661013140387e-05,
"loss": 3.6947,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.057822418389335e-05,
"loss": 3.7041,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056983823638283e-05,
"loss": 3.7044,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056145228887231e-05,
"loss": 3.6968,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055306634136179e-05,
"loss": 3.6861,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.054468039385127e-05,
"loss": 3.6824,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053629444634075e-05,
"loss": 3.6946,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.052792487763396e-05,
"loss": 3.7011,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051953893012344e-05,
"loss": 3.6977,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.051115298261292e-05,
"loss": 3.6966,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.05027670351024e-05,
"loss": 3.6827,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.0494397466395614e-05,
"loss": 3.692,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.048602789768882e-05,
"loss": 3.6874,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.04776419501783e-05,
"loss": 3.6941,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.046925600266778e-05,
"loss": 3.6985,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046087005515726e-05,
"loss": 3.7108,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045250048645047e-05,
"loss": 3.6985,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044411453893995e-05,
"loss": 3.6845,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043572859142943e-05,
"loss": 3.6904,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042734264391891e-05,
"loss": 3.689,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041895669640839e-05,
"loss": 3.701,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.041057074889787e-05,
"loss": 3.6898,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040218480138735e-05,
"loss": 3.6993,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039379885387683e-05,
"loss": 3.6923,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038542928517005e-05,
"loss": 3.6819,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.037704333765953e-05,
"loss": 3.6904,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.0368657390149e-05,
"loss": 3.6842,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.036028782144222e-05,
"loss": 3.6835,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.03519018739317e-05,
"loss": 3.6955,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0343515926421177e-05,
"loss": 3.6886,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.033512997891065e-05,
"loss": 3.6846,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.0326760410203866e-05,
"loss": 3.6845,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.0318374462693346e-05,
"loss": 3.6849,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.0309988515182826e-05,
"loss": 3.6952,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.0301602567672305e-05,
"loss": 3.6856,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.029323299896552e-05,
"loss": 3.7024,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028486343025873e-05,
"loss": 3.6979,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027647748274821e-05,
"loss": 3.6965,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026809153523769e-05,
"loss": 3.691,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025970558772717e-05,
"loss": 3.6776,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025131964021665e-05,
"loss": 3.6946,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024295007150986e-05,
"loss": 3.6908,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023456412399934e-05,
"loss": 3.6866,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022617817648882e-05,
"loss": 3.6803,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.02177922289783e-05,
"loss": 3.6918,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.0209422660271515e-05,
"loss": 3.679,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0201036712760995e-05,
"loss": 3.6882,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.0192650765250475e-05,
"loss": 3.679,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.018426481773995e-05,
"loss": 3.6928,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017587887022943e-05,
"loss": 3.677,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.0167509301522644e-05,
"loss": 3.7003,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.0159123354012124e-05,
"loss": 3.6882,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.01507374065016e-05,
"loss": 3.7012,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.014235145899108e-05,
"loss": 3.676,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013396551148056e-05,
"loss": 3.6962,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012557956397004e-05,
"loss": 3.6893,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011719361645952e-05,
"loss": 3.6951,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.0108807668949e-05,
"loss": 3.6899,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.010043810024221e-05,
"loss": 3.6896,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009205215273169e-05,
"loss": 3.6867,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008366620522117e-05,
"loss": 3.7003,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.007528025771065e-05,
"loss": 3.6788,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006691068900386e-05,
"loss": 3.6926,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005854112029707e-05,
"loss": 3.6881,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.005015517278655e-05,
"loss": 3.6842,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004176922527603e-05,
"loss": 3.6881,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003338327776551e-05,
"loss": 3.6853,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.002499733025499e-05,
"loss": 3.696,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001661138274447e-05,
"loss": 3.6692,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000822543523395e-05,
"loss": 3.6904,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 3.8539795875549316,
"eval_runtime": 303.532,
"eval_samples_per_second": 1257.169,
"eval_steps_per_second": 39.287,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999983948772343e-05,
"loss": 3.6828,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999145354021292e-05,
"loss": 3.6758,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.99830675927024e-05,
"loss": 3.6819,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997468164519188e-05,
"loss": 3.6855,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996629569768136e-05,
"loss": 3.6994,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995790975017084e-05,
"loss": 3.679,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994952380266031e-05,
"loss": 3.6786,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.9941154233953526e-05,
"loss": 3.678,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.9932768286443006e-05,
"loss": 3.6789,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992438233893248e-05,
"loss": 3.6904,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991599639142196e-05,
"loss": 3.6784,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990761044391144e-05,
"loss": 3.6875,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.9899240875204655e-05,
"loss": 3.6771,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890854927694135e-05,
"loss": 3.6762,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9882468980183615e-05,
"loss": 3.6772,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9874083032673095e-05,
"loss": 3.6729,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.9865697085162575e-05,
"loss": 3.6739,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.9857311137652055e-05,
"loss": 3.6778,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848925190141535e-05,
"loss": 3.679,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.9840539242631015e-05,
"loss": 3.6834,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.9832169673924224e-05,
"loss": 3.684,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.982380010521743e-05,
"loss": 3.6892,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981541415770691e-05,
"loss": 3.6732,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980702821019639e-05,
"loss": 3.6812,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979864226268587e-05,
"loss": 3.6721,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.979027269397909e-05,
"loss": 3.6874,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.978188674646857e-05,
"loss": 3.6739,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977350079895805e-05,
"loss": 3.6736,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976511485144753e-05,
"loss": 3.673,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975674528274074e-05,
"loss": 3.6701,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974835933523022e-05,
"loss": 3.6699,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.97399733877197e-05,
"loss": 3.6855,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973158744020918e-05,
"loss": 3.6802,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972320149269866e-05,
"loss": 3.6799,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971481554518814e-05,
"loss": 3.6726,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970642959767762e-05,
"loss": 3.6854,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.9698060028970827e-05,
"loss": 3.6806,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.9689674081460306e-05,
"loss": 3.6674,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968128813394979e-05,
"loss": 3.6668,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967290218643927e-05,
"loss": 3.6682,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966451623892875e-05,
"loss": 3.6718,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965613029141823e-05,
"loss": 3.6796,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964774434390771e-05,
"loss": 3.6741,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963935839639719e-05,
"loss": 3.6685,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.96309888276904e-05,
"loss": 3.6817,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962260288017988e-05,
"loss": 3.6692,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961421693266936e-05,
"loss": 3.6752,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960584736396257e-05,
"loss": 3.6617,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959746141645205e-05,
"loss": 3.6511,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958907546894153e-05,
"loss": 3.6817,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.958068952143101e-05,
"loss": 3.6709,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957230357392049e-05,
"loss": 3.6729,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956391762640997e-05,
"loss": 3.6672,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955553167889945e-05,
"loss": 3.666,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954714573138893e-05,
"loss": 3.6606,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953877616268215e-05,
"loss": 3.6716,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.953039021517162e-05,
"loss": 3.663,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.95220042676611e-05,
"loss": 3.67,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951361832015058e-05,
"loss": 3.6794,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950524875144379e-05,
"loss": 3.6615,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949686280393327e-05,
"loss": 3.6596,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948847685642275e-05,
"loss": 3.677,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.948009090891223e-05,
"loss": 3.6608,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947173771900918e-05,
"loss": 3.6592,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946335177149866e-05,
"loss": 3.6757,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945496582398814e-05,
"loss": 3.6667,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.944657987647762e-05,
"loss": 3.6573,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9438193928967094e-05,
"loss": 3.6672,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.9429807981456573e-05,
"loss": 3.6572,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.9421422033946053e-05,
"loss": 3.6572,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.9413036086435533e-05,
"loss": 3.6765,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940466651772874e-05,
"loss": 3.6711,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939628057021822e-05,
"loss": 3.6721,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938791100151144e-05,
"loss": 3.6716,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937952505400092e-05,
"loss": 3.6882,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.93711391064904e-05,
"loss": 3.6608,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936275315897988e-05,
"loss": 3.6723,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935436721146936e-05,
"loss": 3.6728,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934598126395884e-05,
"loss": 3.6622,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933761169525205e-05,
"loss": 3.6631,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932922574774153e-05,
"loss": 3.6798,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.932083980023101e-05,
"loss": 3.6735,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.931245385272049e-05,
"loss": 3.6732,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930406790520997e-05,
"loss": 3.6576,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929568195769945e-05,
"loss": 3.6521,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928729601018893e-05,
"loss": 3.6689,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.9278926441482136e-05,
"loss": 3.6733,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.9270540493971616e-05,
"loss": 3.6703,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.92621545464611e-05,
"loss": 3.6695,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925376859895058e-05,
"loss": 3.6556,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924538265144006e-05,
"loss": 3.6629,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923701308273327e-05,
"loss": 3.6608,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922862713522275e-05,
"loss": 3.6631,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.922024118771223e-05,
"loss": 3.6739,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.921185524020171e-05,
"loss": 3.6806,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.920348567149492e-05,
"loss": 3.6741,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.91950997239844e-05,
"loss": 3.661,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.918671377647388e-05,
"loss": 3.6593,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.917832782896336e-05,
"loss": 3.663,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916994188145284e-05,
"loss": 3.6712,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916155593394232e-05,
"loss": 3.6637,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.91531699864318e-05,
"loss": 3.6728,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914478403892128e-05,
"loss": 3.6653,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.9136414470214496e-05,
"loss": 3.6582,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.9128044901507705e-05,
"loss": 3.664,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.9119658953997185e-05,
"loss": 3.6564,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.9111273006486665e-05,
"loss": 3.656,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9102887058976145e-05,
"loss": 3.6687,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.9094501111465625e-05,
"loss": 3.6629,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.9086131542758834e-05,
"loss": 3.6586,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.9077745595248314e-05,
"loss": 3.6539,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.9069359647737794e-05,
"loss": 3.6566,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060973700227274e-05,
"loss": 3.6683,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.9052587752716754e-05,
"loss": 3.657,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904421818400997e-05,
"loss": 3.6776,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.903583223649945e-05,
"loss": 3.6731,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.902744628898892e-05,
"loss": 3.6685,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.90190603414784e-05,
"loss": 3.6585,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.901067439396788e-05,
"loss": 3.6554,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900228844645736e-05,
"loss": 3.6659,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899391887775057e-05,
"loss": 3.6626,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898553293024005e-05,
"loss": 3.659,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897714698272953e-05,
"loss": 3.6552,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.896876103521901e-05,
"loss": 3.6661,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.896039146651223e-05,
"loss": 3.656,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895200551900171e-05,
"loss": 3.6582,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.894361957149119e-05,
"loss": 3.6501,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.893523362398067e-05,
"loss": 3.6673,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.892684767647015e-05,
"loss": 3.6524,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.891847810776336e-05,
"loss": 3.6674,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.891009216025284e-05,
"loss": 3.6627,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.890170621274232e-05,
"loss": 3.6732,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.8893320265231797e-05,
"loss": 3.6516,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.8884934317721277e-05,
"loss": 3.6696,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.8876564749014486e-05,
"loss": 3.6577,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.8868178801503966e-05,
"loss": 3.6688,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.8859792853993446e-05,
"loss": 3.6666,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885140690648293e-05,
"loss": 3.6598,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884302095897241e-05,
"loss": 3.6632,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883463501146189e-05,
"loss": 3.674,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882624906395137e-05,
"loss": 3.6508,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881787949524458e-05,
"loss": 3.6642,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880949354773406e-05,
"loss": 3.665,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880110760022354e-05,
"loss": 3.6617,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879272165271302e-05,
"loss": 3.6551,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.87843357052025e-05,
"loss": 3.6583,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877594975769198e-05,
"loss": 3.6675,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876756381018146e-05,
"loss": 3.647,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.8759177862670934e-05,
"loss": 3.6628,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.8482131958007812,
"eval_runtime": 322.4983,
"eval_samples_per_second": 1183.234,
"eval_steps_per_second": 36.977,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875080829396415e-05,
"loss": 3.6567,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874242234645363e-05,
"loss": 3.6502,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.8734052777746846e-05,
"loss": 3.6548,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.8725666830236326e-05,
"loss": 3.6628,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8717280882725806e-05,
"loss": 3.6753,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.8708894935215286e-05,
"loss": 3.6512,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.870050898770476e-05,
"loss": 3.6528,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.8692139418997975e-05,
"loss": 3.6573,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.8683753471487455e-05,
"loss": 3.6454,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.8675367523976935e-05,
"loss": 3.6677,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.866698157646641e-05,
"loss": 3.6514,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.865859562895589e-05,
"loss": 3.657,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.8650226060249104e-05,
"loss": 3.6612,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641840112738584e-05,
"loss": 3.6467,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8633454165228064e-05,
"loss": 3.6464,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8625068217717544e-05,
"loss": 3.6467,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.8616682270207024e-05,
"loss": 3.6475,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.8608296322696503e-05,
"loss": 3.6549,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.8599910375185983e-05,
"loss": 3.6472,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.8591524427675463e-05,
"loss": 3.6572,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858315485896867e-05,
"loss": 3.6603,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857478529026188e-05,
"loss": 3.665,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856639934275136e-05,
"loss": 3.6536,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855801339524084e-05,
"loss": 3.65,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854962744773032e-05,
"loss": 3.6485,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854125787902354e-05,
"loss": 3.6611,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853287193151302e-05,
"loss": 3.6511,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.85244859840025e-05,
"loss": 3.6488,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851610003649198e-05,
"loss": 3.6453,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.8507730467785186e-05,
"loss": 3.6435,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.8499344520274666e-05,
"loss": 3.6412,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.8490958572764146e-05,
"loss": 3.6609,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.8482572625253626e-05,
"loss": 3.6574,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.8474186677743106e-05,
"loss": 3.6553,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.8465800730232586e-05,
"loss": 3.6481,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.8457414782722066e-05,
"loss": 3.6524,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.8449045214015275e-05,
"loss": 3.6597,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.8440659266504755e-05,
"loss": 3.6432,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843227331899424e-05,
"loss": 3.6432,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842388737148372e-05,
"loss": 3.6404,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.84155014239732e-05,
"loss": 3.6439,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840713185526641e-05,
"loss": 3.6549,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839874590775589e-05,
"loss": 3.6489,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.839035996024537e-05,
"loss": 3.6439,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.838197401273485e-05,
"loss": 3.6556,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837358806522433e-05,
"loss": 3.6467,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836520211771381e-05,
"loss": 3.6465,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835683254900702e-05,
"loss": 3.6411,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.83484466014965e-05,
"loss": 3.6205,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.834006065398598e-05,
"loss": 3.6582,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833167470647546e-05,
"loss": 3.6435,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832328875896494e-05,
"loss": 3.6537,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.831490281145442e-05,
"loss": 3.638,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.83065168639439e-05,
"loss": 3.6432,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829813091643338e-05,
"loss": 3.6355,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.8289761347726595e-05,
"loss": 3.6426,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828137540021607e-05,
"loss": 3.6395,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827298945270555e-05,
"loss": 3.6431,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826460350519503e-05,
"loss": 3.6562,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.8256233936488244e-05,
"loss": 3.6353,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824784798897772e-05,
"loss": 3.6339,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.82394620414672e-05,
"loss": 3.6517,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.823107609395668e-05,
"loss": 3.6387,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.822270652524989e-05,
"loss": 3.6341,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.821432057773937e-05,
"loss": 3.6476,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.820593463022885e-05,
"loss": 3.6466,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.819754868271833e-05,
"loss": 3.632,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.818919549281528e-05,
"loss": 3.6427,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818080954530476e-05,
"loss": 3.6303,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817242359779424e-05,
"loss": 3.6379,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816403765028371e-05,
"loss": 3.6495,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815565170277319e-05,
"loss": 3.6465,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814726575526267e-05,
"loss": 3.6497,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.813889618655589e-05,
"loss": 3.6475,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.813051023904537e-05,
"loss": 3.6623,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812212429153485e-05,
"loss": 3.6332,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811373834402433e-05,
"loss": 3.6533,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810535239651381e-05,
"loss": 3.6426,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.809696644900329e-05,
"loss": 3.6402,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.8088596880296496e-05,
"loss": 3.6403,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.8080210932785976e-05,
"loss": 3.6548,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.8071824985275456e-05,
"loss": 3.6485,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.8063439037764936e-05,
"loss": 3.6511,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.8055069469058145e-05,
"loss": 3.6305,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.8046683521547625e-05,
"loss": 3.6304,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.8038297574037105e-05,
"loss": 3.6413,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.8029911626526585e-05,
"loss": 3.6484,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.8021525679016065e-05,
"loss": 3.6403,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.801315611030928e-05,
"loss": 3.6478,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.800477016279876e-05,
"loss": 3.6326,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799638421528824e-05,
"loss": 3.6397,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.798799826777772e-05,
"loss": 3.6358,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797962869907093e-05,
"loss": 3.6366,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797124275156041e-05,
"loss": 3.6479,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796285680404989e-05,
"loss": 3.6554,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795447085653937e-05,
"loss": 3.6503,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.794608490902885e-05,
"loss": 3.6357,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793769896151833e-05,
"loss": 3.6355,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792931301400781e-05,
"loss": 3.6402,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792092706649729e-05,
"loss": 3.6457,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.7912557497790505e-05,
"loss": 3.6396,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.7904171550279985e-05,
"loss": 3.6459,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.7895785602769465e-05,
"loss": 3.6427,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.7887416034062674e-05,
"loss": 3.636,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.7879030086552154e-05,
"loss": 3.637,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.7870644139041634e-05,
"loss": 3.6305,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.7862258191531114e-05,
"loss": 3.6343,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.7853872244020594e-05,
"loss": 3.6451,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.7845486296510074e-05,
"loss": 3.6384,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783711672780328e-05,
"loss": 3.6325,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782873078029276e-05,
"loss": 3.6337,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.782034483278224e-05,
"loss": 3.6267,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781195888527172e-05,
"loss": 3.6446,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.78035729377612e-05,
"loss": 3.6346,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.779518699025068e-05,
"loss": 3.652,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.77868174215439e-05,
"loss": 3.6458,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777843147403338e-05,
"loss": 3.6496,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.777004552652285e-05,
"loss": 3.6325,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776165957901233e-05,
"loss": 3.6329,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.775329001030555e-05,
"loss": 3.6413,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774490406279502e-05,
"loss": 3.6409,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.77365181152845e-05,
"loss": 3.6338,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772813216777398e-05,
"loss": 3.6294,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771974622026346e-05,
"loss": 3.6418,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.7711376651556676e-05,
"loss": 3.6344,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.7702990704046156e-05,
"loss": 3.6331,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.7694604756535636e-05,
"loss": 3.6306,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.7686218809025116e-05,
"loss": 3.6384,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.7677832861514596e-05,
"loss": 3.6303,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.7669463292807805e-05,
"loss": 3.6441,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.7661077345297285e-05,
"loss": 3.6382,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.7652691397786765e-05,
"loss": 3.6549,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.7644305450276245e-05,
"loss": 3.6257,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.7635919502765725e-05,
"loss": 3.6461,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.7627533555255205e-05,
"loss": 3.6342,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.7619147607744685e-05,
"loss": 3.6461,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.7610761660234165e-05,
"loss": 3.6398,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760239209152738e-05,
"loss": 3.6365,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759400614401686e-05,
"loss": 3.6397,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758562019650634e-05,
"loss": 3.6544,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.757725062779955e-05,
"loss": 3.6262,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.756886468028903e-05,
"loss": 3.6436,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.756049511158224e-05,
"loss": 3.6393,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755210916407172e-05,
"loss": 3.6346,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.75437232165612e-05,
"loss": 3.6307,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.753533726905068e-05,
"loss": 3.636,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752695132154016e-05,
"loss": 3.6403,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751856537402964e-05,
"loss": 3.6334,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.751017942651912e-05,
"loss": 3.6345,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 3.8461179733276367,
"eval_runtime": 311.3368,
"eval_samples_per_second": 1225.653,
"eval_steps_per_second": 38.303,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.75017934790086e-05,
"loss": 3.6288,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.749340753149808e-05,
"loss": 3.6264,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748502158398756e-05,
"loss": 3.6291,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747663563647704e-05,
"loss": 3.6406,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.7468266067770254e-05,
"loss": 3.6497,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.7459880120259734e-05,
"loss": 3.6305,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.745149417274921e-05,
"loss": 3.6305,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744310822523869e-05,
"loss": 3.6314,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743472227772817e-05,
"loss": 3.6242,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742633633021765e-05,
"loss": 3.6419,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741795038270713e-05,
"loss": 3.6286,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740956443519661e-05,
"loss": 3.6355,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.7401194866489816e-05,
"loss": 3.6379,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.7392808918979296e-05,
"loss": 3.6217,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738442297146878e-05,
"loss": 3.6246,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737603702395826e-05,
"loss": 3.623,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736766745525147e-05,
"loss": 3.6279,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735928150774095e-05,
"loss": 3.6285,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735089556023043e-05,
"loss": 3.6275,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734250961271991e-05,
"loss": 3.6344,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733412366520939e-05,
"loss": 3.6357,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.73257540965026e-05,
"loss": 3.638,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731736814899208e-05,
"loss": 3.6316,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.730898220148156e-05,
"loss": 3.6248,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.730059625397104e-05,
"loss": 3.6278,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.729222668526425e-05,
"loss": 3.6355,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.728384073775374e-05,
"loss": 3.625,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727545479024322e-05,
"loss": 3.6309,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.72670688427327e-05,
"loss": 3.6229,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.7258699274025906e-05,
"loss": 3.6205,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.7250313326515386e-05,
"loss": 3.6201,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.7241927379004866e-05,
"loss": 3.6328,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.7233541431494346e-05,
"loss": 3.6381,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.7225155483983826e-05,
"loss": 3.6298,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.7216785915277035e-05,
"loss": 3.6289,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.7208399967766515e-05,
"loss": 3.6251,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.7200014020255995e-05,
"loss": 3.6394,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.7191628072745475e-05,
"loss": 3.6238,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.7183242125234954e-05,
"loss": 3.6198,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717487255652817e-05,
"loss": 3.6171,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716648660901765e-05,
"loss": 3.6246,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715810066150713e-05,
"loss": 3.6254,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.714971471399661e-05,
"loss": 3.6288,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714134514528982e-05,
"loss": 3.625,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.71329591977793e-05,
"loss": 3.63,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712457325026878e-05,
"loss": 3.624,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711618730275826e-05,
"loss": 3.6226,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710781773405147e-05,
"loss": 3.619,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709943178654095e-05,
"loss": 3.5984,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709104583903043e-05,
"loss": 3.6349,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708265989151991e-05,
"loss": 3.6191,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.7074290322813124e-05,
"loss": 3.6311,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.7065904375302604e-05,
"loss": 3.6206,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.7057518427792084e-05,
"loss": 3.6186,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.7049132480281564e-05,
"loss": 3.6113,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.704076291157477e-05,
"loss": 3.6218,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703237696406425e-05,
"loss": 3.6193,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702399101655373e-05,
"loss": 3.6162,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.701560506904321e-05,
"loss": 3.6357,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.700721912153269e-05,
"loss": 3.6202,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.6998833174022166e-05,
"loss": 3.6065,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.699046360531538e-05,
"loss": 3.6275,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698207765780486e-05,
"loss": 3.6177,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.697369171029434e-05,
"loss": 3.6136,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696530576278382e-05,
"loss": 3.6244,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695693619407704e-05,
"loss": 3.6199,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694855024656652e-05,
"loss": 3.6101,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.694016429905599e-05,
"loss": 3.6203,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693177835154547e-05,
"loss": 3.6097,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692339240403495e-05,
"loss": 3.6146,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691500645652443e-05,
"loss": 3.626,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690662050901391e-05,
"loss": 3.6247,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689823456150339e-05,
"loss": 3.6261,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.68898649927966e-05,
"loss": 3.6216,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688147904528608e-05,
"loss": 3.6406,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.687309309777556e-05,
"loss": 3.6139,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.6864707150265046e-05,
"loss": 3.629,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.6856337581558255e-05,
"loss": 3.6222,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.6847951634047735e-05,
"loss": 3.6175,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.6839565686537215e-05,
"loss": 3.6173,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.6831179739026695e-05,
"loss": 3.634,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.6822793791516175e-05,
"loss": 3.6228,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.6814407844005655e-05,
"loss": 3.6335,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.6806038275298864e-05,
"loss": 3.6073,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.6797652327788344e-05,
"loss": 3.6074,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.6789266380277824e-05,
"loss": 3.6203,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.6780880432767304e-05,
"loss": 3.6294,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677251086406051e-05,
"loss": 3.6167,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676412491655e-05,
"loss": 3.6242,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675573896903948e-05,
"loss": 3.6169,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.674735302152896e-05,
"loss": 3.6123,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.673898345282217e-05,
"loss": 3.6156,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.673059750531165e-05,
"loss": 3.6152,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672221155780113e-05,
"loss": 3.6253,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671382561029061e-05,
"loss": 3.6359,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670545604158382e-05,
"loss": 3.6315,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.66970700940733e-05,
"loss": 3.6125,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668868414656278e-05,
"loss": 3.611,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.668029819905226e-05,
"loss": 3.6174,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667191225154174e-05,
"loss": 3.6218,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666352630403122e-05,
"loss": 3.6212,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.66551403565207e-05,
"loss": 3.6228,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.6646770787813914e-05,
"loss": 3.6228,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.6638384840303393e-05,
"loss": 3.6123,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.6629998892792873e-05,
"loss": 3.6175,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662161294528235e-05,
"loss": 3.6092,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.6613226997771827e-05,
"loss": 3.6115,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6604841050261307e-05,
"loss": 3.6235,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.659647148155452e-05,
"loss": 3.6174,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.6588085534044e-05,
"loss": 3.6094,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.6579699586533476e-05,
"loss": 3.6139,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.6571313639022955e-05,
"loss": 3.6037,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.6562927691512435e-05,
"loss": 3.622,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655454174400192e-05,
"loss": 3.615,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654617217529513e-05,
"loss": 3.6247,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.653778622778461e-05,
"loss": 3.6252,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652940028027409e-05,
"loss": 3.6266,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652101433276357e-05,
"loss": 3.6124,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651262838525305e-05,
"loss": 3.614,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650425881654626e-05,
"loss": 3.618,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649587286903574e-05,
"loss": 3.6228,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648748692152522e-05,
"loss": 3.6116,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.64791009740147e-05,
"loss": 3.6066,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.647071502650418e-05,
"loss": 3.6205,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646234545779739e-05,
"loss": 3.6115,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6453959510286876e-05,
"loss": 3.6104,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.6445573562776356e-05,
"loss": 3.6088,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.6437187615265836e-05,
"loss": 3.6208,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.6428818046559045e-05,
"loss": 3.6056,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.6420432099048525e-05,
"loss": 3.6246,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.6412046151538005e-05,
"loss": 3.6177,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.6403660204027485e-05,
"loss": 3.6311,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.6395290635320694e-05,
"loss": 3.6024,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.6386904687810174e-05,
"loss": 3.6219,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.6378518740299654e-05,
"loss": 3.6204,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.6370132792789134e-05,
"loss": 3.62,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.6361746845278614e-05,
"loss": 3.6202,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.6353360897768094e-05,
"loss": 3.6155,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.6344974950257574e-05,
"loss": 3.6162,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633660538155079e-05,
"loss": 3.6311,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632821943404027e-05,
"loss": 3.6105,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.631983348652975e-05,
"loss": 3.62,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631144753901923e-05,
"loss": 3.6185,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630307797031244e-05,
"loss": 3.6121,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629469202280192e-05,
"loss": 3.6117,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.62863060752914e-05,
"loss": 3.6172,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627792012778088e-05,
"loss": 3.6177,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626955055907409e-05,
"loss": 3.6176,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626116461156357e-05,
"loss": 3.6098,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.844015121459961,
"eval_runtime": 306.1176,
"eval_samples_per_second": 1246.55,
"eval_steps_per_second": 38.956,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.625277866405305e-05,
"loss": 3.6113,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.624439271654253e-05,
"loss": 3.6063,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.623600676903201e-05,
"loss": 3.611,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.622763720032522e-05,
"loss": 3.6182,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.62192512528147e-05,
"loss": 3.6265,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.621086530530418e-05,
"loss": 3.6117,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.620247935779366e-05,
"loss": 3.6103,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.619410978908687e-05,
"loss": 3.6105,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.618572384157635e-05,
"loss": 3.6017,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.617733789406583e-05,
"loss": 3.6191,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.6168951946555305e-05,
"loss": 3.6086,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.6160565999044785e-05,
"loss": 3.6182,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.6152196430338e-05,
"loss": 3.6158,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.614381048282748e-05,
"loss": 3.5991,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.613542453531696e-05,
"loss": 3.6062,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.612703858780644e-05,
"loss": 3.5986,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.611865264029592e-05,
"loss": 3.6106,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.6110283071589137e-05,
"loss": 3.6099,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.610189712407861e-05,
"loss": 3.6033,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.609351117656809e-05,
"loss": 3.6116,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.608512522905757e-05,
"loss": 3.6146,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.607675566035078e-05,
"loss": 3.618,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.606836971284026e-05,
"loss": 3.6106,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.605998376532974e-05,
"loss": 3.6089,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.605159781781922e-05,
"loss": 3.6076,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.6043228249112435e-05,
"loss": 3.6124,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.6034842301601914e-05,
"loss": 3.603,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.6026456354091394e-05,
"loss": 3.6091,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.6018070406580874e-05,
"loss": 3.6058,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.6009700837874083e-05,
"loss": 3.6003,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.6001314890363563e-05,
"loss": 3.6021,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.5992928942853043e-05,
"loss": 3.6118,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598454299534252e-05,
"loss": 3.6096,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.5976157047832e-05,
"loss": 3.6184,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596778747912521e-05,
"loss": 3.6028,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595940153161469e-05,
"loss": 3.6069,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595101558410417e-05,
"loss": 3.6193,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.594262963659365e-05,
"loss": 3.6,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.593426006788687e-05,
"loss": 3.6018,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.592587412037635e-05,
"loss": 3.5953,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.591748817286583e-05,
"loss": 3.6041,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.590910222535531e-05,
"loss": 3.6034,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.590071627784479e-05,
"loss": 3.607,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.5892346709138e-05,
"loss": 3.6068,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.588396076162748e-05,
"loss": 3.605,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.587557481411696e-05,
"loss": 3.6101,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.586718886660644e-05,
"loss": 3.5978,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.5858819297899646e-05,
"loss": 3.6008,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.5850433350389126e-05,
"loss": 3.5778,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.5842047402878606e-05,
"loss": 3.6146,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.583366145536809e-05,
"loss": 3.5994,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.582527550785757e-05,
"loss": 3.6075,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581690593915078e-05,
"loss": 3.6023,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.580851999164026e-05,
"loss": 3.5977,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.580013404412974e-05,
"loss": 3.5896,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579174809661922e-05,
"loss": 3.6001,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.57833621491087e-05,
"loss": 3.6021,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.577497620159818e-05,
"loss": 3.5945,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.576659025408766e-05,
"loss": 3.6145,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.575820430657714e-05,
"loss": 3.6019,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.574983473787035e-05,
"loss": 3.582,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.574144879035983e-05,
"loss": 3.6088,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.573306284284931e-05,
"loss": 3.6001,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.572467689533879e-05,
"loss": 3.5924,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.571629094782827e-05,
"loss": 3.6011,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.570790500031775e-05,
"loss": 3.6029,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.5699535431610966e-05,
"loss": 3.5895,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.569114948410044e-05,
"loss": 3.6031,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.568276353658992e-05,
"loss": 3.5898,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.56743775890794e-05,
"loss": 3.5908,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566599164156888e-05,
"loss": 3.6089,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565762207286209e-05,
"loss": 3.5997,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564923612535157e-05,
"loss": 3.6072,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.564085017784105e-05,
"loss": 3.6043,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.563246423033053e-05,
"loss": 3.6149,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.5624094661623744e-05,
"loss": 3.5963,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.5615708714113224e-05,
"loss": 3.6111,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.5607322766602704e-05,
"loss": 3.5982,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.5598936819092184e-05,
"loss": 3.5996,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.559056725038539e-05,
"loss": 3.5976,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.558218130287487e-05,
"loss": 3.612,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.557379535536435e-05,
"loss": 3.6063,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.556540940785383e-05,
"loss": 3.6139,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.555703983914704e-05,
"loss": 3.5893,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.554865389163652e-05,
"loss": 3.5876,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.5540267944126e-05,
"loss": 3.6018,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.553188199661548e-05,
"loss": 3.608,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.55235124279087e-05,
"loss": 3.596,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.551512648039818e-05,
"loss": 3.6068,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.550674053288766e-05,
"loss": 3.5978,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.549835458537714e-05,
"loss": 3.5899,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.548998501667035e-05,
"loss": 3.5967,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548159906915983e-05,
"loss": 3.5958,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.5473213121649307e-05,
"loss": 3.6093,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.5464827174138787e-05,
"loss": 3.6114,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.5456457605431996e-05,
"loss": 3.6152,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.5448071657921476e-05,
"loss": 3.5882,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.5439685710410956e-05,
"loss": 3.5937,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.5431299762900436e-05,
"loss": 3.5981,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.542293019419365e-05,
"loss": 3.6036,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.541454424668313e-05,
"loss": 3.5986,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.540615829917261e-05,
"loss": 3.6045,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.539777235166209e-05,
"loss": 3.5995,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.53894027829553e-05,
"loss": 3.5962,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.538101683544478e-05,
"loss": 3.599,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.537263088793426e-05,
"loss": 3.5879,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.536424494042374e-05,
"loss": 3.5943,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.535587537171695e-05,
"loss": 3.6001,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.534748942420643e-05,
"loss": 3.6016,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.533910347669591e-05,
"loss": 3.5885,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.533071752918539e-05,
"loss": 3.5952,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.532233158167487e-05,
"loss": 3.5822,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.5313962012968085e-05,
"loss": 3.6075,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.5305576065457565e-05,
"loss": 3.5954,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.5297190117947045e-05,
"loss": 3.6067,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.5288804170436525e-05,
"loss": 3.6014,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.5280434601729734e-05,
"loss": 3.6083,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.5272048654219214e-05,
"loss": 3.5937,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.5263662706708694e-05,
"loss": 3.5926,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.5255276759198174e-05,
"loss": 3.6043,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524690719049138e-05,
"loss": 3.6002,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523852124298086e-05,
"loss": 3.5961,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.523013529547034e-05,
"loss": 3.5877,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.522174934795982e-05,
"loss": 3.5981,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.521337977925304e-05,
"loss": 3.5949,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.520499383174252e-05,
"loss": 3.5935,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.5196607884232e-05,
"loss": 3.5881,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.518822193672148e-05,
"loss": 3.5986,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.517983598921096e-05,
"loss": 3.5855,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.517146642050417e-05,
"loss": 3.6072,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.516308047299365e-05,
"loss": 3.5973,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.515469452548313e-05,
"loss": 3.6129,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.514630857797261e-05,
"loss": 3.5861,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.5137939009265817e-05,
"loss": 3.6041,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.5129553061755297e-05,
"loss": 3.5969,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.5121167114244776e-05,
"loss": 3.5999,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.511278116673426e-05,
"loss": 3.6011,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.510439521922374e-05,
"loss": 3.5947,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.509600927171322e-05,
"loss": 3.5991,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.508763970300643e-05,
"loss": 3.6102,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.507925375549591e-05,
"loss": 3.592,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.507086780798539e-05,
"loss": 3.5996,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.506248186047487e-05,
"loss": 3.5966,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.5054095912964345e-05,
"loss": 3.5945,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.504572634425756e-05,
"loss": 3.5939,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.503734039674704e-05,
"loss": 3.5951,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.5028954449236514e-05,
"loss": 3.5961,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.5020568501726e-05,
"loss": 3.5989,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501218255421548e-05,
"loss": 3.5897,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 3.84383225440979,
"eval_runtime": 305.8389,
"eval_samples_per_second": 1247.686,
"eval_steps_per_second": 38.991,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.50038129855087e-05,
"loss": 3.6049,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.499542703799817e-05,
"loss": 3.5813,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.498704109048765e-05,
"loss": 3.5908,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.497865514297713e-05,
"loss": 3.6027,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.4970285574270346e-05,
"loss": 3.6026,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.496189962675982e-05,
"loss": 3.5939,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.49535136792493e-05,
"loss": 3.5963,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.494512773173878e-05,
"loss": 3.5911,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.493674178422826e-05,
"loss": 3.5838,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.492837221552147e-05,
"loss": 3.5935,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.4919986268010955e-05,
"loss": 3.5942,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.4911600320500435e-05,
"loss": 3.5944,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.4903214372989915e-05,
"loss": 3.5979,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.4894828425479395e-05,
"loss": 3.5807,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.4886458856772604e-05,
"loss": 3.5882,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.4878072909262084e-05,
"loss": 3.5812,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.4869686961751564e-05,
"loss": 3.5892,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.4861301014241043e-05,
"loss": 3.5909,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.485293144553425e-05,
"loss": 3.5839,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.484454549802373e-05,
"loss": 3.5918,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.483615955051321e-05,
"loss": 3.5956,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.482777360300269e-05,
"loss": 3.5998,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.48194040342959e-05,
"loss": 3.5944,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.481101808678539e-05,
"loss": 3.5872,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.480263213927487e-05,
"loss": 3.5922,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.479424619176435e-05,
"loss": 3.5945,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.478586024425383e-05,
"loss": 3.5859,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.477749067554704e-05,
"loss": 3.5887,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.476910472803652e-05,
"loss": 3.5839,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.4760718780526e-05,
"loss": 3.5825,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.475233283301548e-05,
"loss": 3.5856,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.4743963264308686e-05,
"loss": 3.588,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.4735577316798166e-05,
"loss": 3.5892,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.4727191369287646e-05,
"loss": 3.6021,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.4718805421777126e-05,
"loss": 3.5867,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.471043585307034e-05,
"loss": 3.5886,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.470204990555982e-05,
"loss": 3.5997,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.46936639580493e-05,
"loss": 3.5808,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.468527801053878e-05,
"loss": 3.5825,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.467689206302826e-05,
"loss": 3.5832,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466852249432147e-05,
"loss": 3.5811,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.466013654681095e-05,
"loss": 3.5834,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.465175059930043e-05,
"loss": 3.5893,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.464336465178991e-05,
"loss": 3.5912,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.463499508308312e-05,
"loss": 3.5858,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.46266091355726e-05,
"loss": 3.5905,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.461822318806208e-05,
"loss": 3.5814,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.460983724055156e-05,
"loss": 3.583,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.460145129304104e-05,
"loss": 3.5606,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.4593081724334256e-05,
"loss": 3.5956,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.4584695776823735e-05,
"loss": 3.5794,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.4576309829313215e-05,
"loss": 3.5885,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.4567923881802695e-05,
"loss": 3.5806,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.4559537934292175e-05,
"loss": 3.5798,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.4551151986781655e-05,
"loss": 3.5732,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.454276603927113e-05,
"loss": 3.5797,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.4534396470564344e-05,
"loss": 3.5854,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.4526010523053824e-05,
"loss": 3.5746,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.45176245755433e-05,
"loss": 3.5966,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.450923862803278e-05,
"loss": 3.5821,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.450086905932599e-05,
"loss": 3.5642,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.449248311181548e-05,
"loss": 3.5886,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.448409716430495e-05,
"loss": 3.5766,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.447571121679443e-05,
"loss": 3.577,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.446732526928391e-05,
"loss": 3.5792,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.445895570057712e-05,
"loss": 3.5856,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.44505697530666e-05,
"loss": 3.5752,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.444218380555608e-05,
"loss": 3.5848,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.443379785804556e-05,
"loss": 3.5682,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.442542828933877e-05,
"loss": 3.5755,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.441704234182825e-05,
"loss": 3.586,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.440865639431773e-05,
"loss": 3.5826,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.440027044680722e-05,
"loss": 3.5882,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.439190087810043e-05,
"loss": 3.5825,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.438351493058991e-05,
"loss": 3.6007,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.437512898307939e-05,
"loss": 3.5771,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.436674303556887e-05,
"loss": 3.5933,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.4358373466862076e-05,
"loss": 3.5769,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.4349987519351556e-05,
"loss": 3.584,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.4341601571841036e-05,
"loss": 3.5747,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.4333215624330516e-05,
"loss": 3.5906,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.4324846055623725e-05,
"loss": 3.5874,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.4316460108113205e-05,
"loss": 3.5968,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.4308074160602685e-05,
"loss": 3.5718,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.429968821309217e-05,
"loss": 3.5704,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.429131864438538e-05,
"loss": 3.58,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.428293269687486e-05,
"loss": 3.5912,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.427454674936434e-05,
"loss": 3.5776,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.426616080185382e-05,
"loss": 3.5901,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.42577748543433e-05,
"loss": 3.5804,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.424940528563651e-05,
"loss": 3.571,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.424101933812599e-05,
"loss": 3.578,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.423263339061547e-05,
"loss": 3.5765,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.422424744310495e-05,
"loss": 3.5887,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.421586149559443e-05,
"loss": 3.5968,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.420749192688764e-05,
"loss": 3.5948,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.4199105979377125e-05,
"loss": 3.5715,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.4190720031866605e-05,
"loss": 3.5765,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.4182334084356085e-05,
"loss": 3.5798,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.4173948136845565e-05,
"loss": 3.5841,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.4165578568138774e-05,
"loss": 3.5832,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.4157192620628254e-05,
"loss": 3.5836,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.4148806673117734e-05,
"loss": 3.5804,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.4140420725607214e-05,
"loss": 3.5772,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.413205115690042e-05,
"loss": 3.5866,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.41236652093899e-05,
"loss": 3.5672,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.411527926187938e-05,
"loss": 3.5749,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.410689331436886e-05,
"loss": 3.5807,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.409852374566207e-05,
"loss": 3.5826,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.409013779815156e-05,
"loss": 3.5745,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.408175185064104e-05,
"loss": 3.5809,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.407336590313052e-05,
"loss": 3.5601,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.406499633442373e-05,
"loss": 3.5852,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.405661038691321e-05,
"loss": 3.5811,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.404822443940269e-05,
"loss": 3.5829,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.403983849189217e-05,
"loss": 3.5866,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.403146892318538e-05,
"loss": 3.5934,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402308297567486e-05,
"loss": 3.5753,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.401469702816434e-05,
"loss": 3.5769,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.400631108065382e-05,
"loss": 3.5839,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.3997941511947026e-05,
"loss": 3.5816,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.398955556443651e-05,
"loss": 3.5741,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.398116961692599e-05,
"loss": 3.5735,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.397278366941547e-05,
"loss": 3.5788,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.396441410070868e-05,
"loss": 3.5783,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.395602815319816e-05,
"loss": 3.5706,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.394764220568764e-05,
"loss": 3.5746,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.393925625817712e-05,
"loss": 3.5777,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.393088668947033e-05,
"loss": 3.5691,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.392250074195981e-05,
"loss": 3.5876,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.391411479444929e-05,
"loss": 3.5773,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.390572884693877e-05,
"loss": 3.5971,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.389734289942825e-05,
"loss": 3.5638,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.3888973330721466e-05,
"loss": 3.5877,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.3880587383210946e-05,
"loss": 3.5841,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.3872201435700426e-05,
"loss": 3.5802,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.3863815488189906e-05,
"loss": 3.5813,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.385542954067938e-05,
"loss": 3.5769,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.3847059971972595e-05,
"loss": 3.5854,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.3838674024462075e-05,
"loss": 3.5877,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.3830288076951555e-05,
"loss": 3.5758,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382190212944103e-05,
"loss": 3.5806,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.3813532560734244e-05,
"loss": 3.5792,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.3805146613223724e-05,
"loss": 3.5751,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.3796760665713204e-05,
"loss": 3.5746,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.3788374718202684e-05,
"loss": 3.5823,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.3779988770692164e-05,
"loss": 3.5756,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.377161920198538e-05,
"loss": 3.5818,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.376323325447485e-05,
"loss": 3.572,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 3.843820810317993,
"eval_runtime": 342.5101,
"eval_samples_per_second": 1114.102,
"eval_steps_per_second": 34.816,
"step": 992160
},
{
"epoch": 1.0,
"learning_rate": 3.375484730696433e-05,
"loss": 3.5812,
"step": 992256
},
{
"epoch": 1.0,
"learning_rate": 3.374646135945381e-05,
"loss": 3.5653,
"step": 992768
},
{
"epoch": 1.0,
"learning_rate": 3.373807541194329e-05,
"loss": 3.5715,
"step": 993280
},
{
"epoch": 1.0,
"learning_rate": 3.372968946443277e-05,
"loss": 3.5858,
"step": 993792
},
{
"epoch": 1.0,
"learning_rate": 3.372131989572598e-05,
"loss": 3.5819,
"step": 994304
},
{
"epoch": 1.0,
"learning_rate": 3.371293394821546e-05,
"loss": 3.5768,
"step": 994816
},
{
"epoch": 1.0,
"learning_rate": 3.370454800070494e-05,
"loss": 3.5749,
"step": 995328
},
{
"epoch": 1.0,
"learning_rate": 3.369616205319442e-05,
"loss": 3.5734,
"step": 995840
},
{
"epoch": 1.0,
"learning_rate": 3.368779248448764e-05,
"loss": 3.5638,
"step": 996352
},
{
"epoch": 1.0,
"learning_rate": 3.367940653697712e-05,
"loss": 3.5819,
"step": 996864
},
{
"epoch": 1.0,
"learning_rate": 3.36710205894666e-05,
"loss": 3.5752,
"step": 997376
},
{
"epoch": 1.0,
"learning_rate": 3.366263464195608e-05,
"loss": 3.5753,
"step": 997888
},
{
"epoch": 1.0,
"learning_rate": 3.3654265073249287e-05,
"loss": 3.5816,
"step": 998400
},
{
"epoch": 1.0,
"learning_rate": 3.3645879125738766e-05,
"loss": 3.5631,
"step": 998912
},
{
"epoch": 1.0,
"learning_rate": 3.3637493178228246e-05,
"loss": 3.5667,
"step": 999424
},
{
"epoch": 1.0,
"learning_rate": 3.3629107230717726e-05,
"loss": 3.5638,
"step": 999936
},
{
"epoch": 1.0,
"learning_rate": 3.3620721283207206e-05,
"loss": 3.5745,
"step": 1000448
},
{
"epoch": 1.0,
"learning_rate": 3.3612351714500415e-05,
"loss": 3.5716,
"step": 1000960
},
{
"epoch": 1.0,
"learning_rate": 3.3603965766989895e-05,
"loss": 3.5672,
"step": 1001472
},
{
"epoch": 1.0,
"learning_rate": 3.3595579819479375e-05,
"loss": 3.5714,
"step": 1001984
},
{
"epoch": 1.0,
"learning_rate": 3.3587193871968855e-05,
"loss": 3.5823,
"step": 1002496
},
{
"epoch": 1.0,
"learning_rate": 3.357882430326207e-05,
"loss": 3.5791,
"step": 1003008
},
{
"epoch": 1.0,
"learning_rate": 3.357043835575155e-05,
"loss": 3.5766,
"step": 1003520
},
{
"epoch": 1.0,
"learning_rate": 3.356205240824103e-05,
"loss": 3.5712,
"step": 1004032
},
{
"epoch": 1.0,
"learning_rate": 3.355366646073051e-05,
"loss": 3.5763,
"step": 1004544
},
{
"epoch": 1.0,
"learning_rate": 3.354529689202372e-05,
"loss": 3.5729,
"step": 1005056
},
{
"epoch": 1.0,
"learning_rate": 3.35369109445132e-05,
"loss": 3.5709,
"step": 1005568
},
{
"epoch": 1.0,
"learning_rate": 3.352852499700268e-05,
"loss": 3.5734,
"step": 1006080
},
{
"epoch": 1.0,
"learning_rate": 3.352013904949216e-05,
"loss": 3.5631,
"step": 1006592
},
{
"epoch": 1.0,
"learning_rate": 3.351176948078537e-05,
"loss": 3.5628,
"step": 1007104
},
{
"epoch": 1.01,
"learning_rate": 3.350338353327485e-05,
"loss": 3.5669,
"step": 1007616
},
{
"epoch": 1.01,
"learning_rate": 3.349499758576433e-05,
"loss": 3.5684,
"step": 1008128
},
{
"epoch": 1.01,
"learning_rate": 3.348661163825381e-05,
"loss": 3.5766,
"step": 1008640
},
{
"epoch": 1.01,
"learning_rate": 3.347822569074329e-05,
"loss": 3.5792,
"step": 1009152
},
{
"epoch": 1.01,
"learning_rate": 3.3469856122036505e-05,
"loss": 3.5684,
"step": 1009664
},
{
"epoch": 1.01,
"learning_rate": 3.3461470174525985e-05,
"loss": 3.5733,
"step": 1010176
},
{
"epoch": 1.01,
"learning_rate": 3.3453084227015465e-05,
"loss": 3.5831,
"step": 1010688
},
{
"epoch": 1.01,
"learning_rate": 3.3444698279504945e-05,
"loss": 3.5589,
"step": 1011200
},
{
"epoch": 1.01,
"learning_rate": 3.3436312331994425e-05,
"loss": 3.5667,
"step": 1011712
},
{
"epoch": 1.01,
"learning_rate": 3.3427926384483905e-05,
"loss": 3.5652,
"step": 1012224
},
{
"epoch": 1.01,
"learning_rate": 3.3419556815777114e-05,
"loss": 3.5641,
"step": 1012736
},
{
"epoch": 1.01,
"learning_rate": 3.3411170868266594e-05,
"loss": 3.5662,
"step": 1013248
},
{
"epoch": 1.01,
"learning_rate": 3.3402784920756074e-05,
"loss": 3.5747,
"step": 1013760
},
{
"epoch": 1.01,
"learning_rate": 3.3394398973245554e-05,
"loss": 3.5747,
"step": 1014272
},
{
"epoch": 1.01,
"learning_rate": 3.338602940453876e-05,
"loss": 3.5644,
"step": 1014784
},
{
"epoch": 1.01,
"learning_rate": 3.337764345702824e-05,
"loss": 3.5724,
"step": 1015296
},
{
"epoch": 1.01,
"learning_rate": 3.336925750951773e-05,
"loss": 3.5643,
"step": 1015808
},
{
"epoch": 1.01,
"learning_rate": 3.336087156200721e-05,
"loss": 3.5625,
"step": 1016320
},
{
"epoch": 1.01,
"learning_rate": 3.335248561449669e-05,
"loss": 3.5464,
"step": 1016832
},
{
"epoch": 1.01,
"learning_rate": 3.33441160457899e-05,
"loss": 3.5758,
"step": 1017344
},
{
"epoch": 1.01,
"learning_rate": 3.333573009827938e-05,
"loss": 3.5645,
"step": 1017856
},
{
"epoch": 1.01,
"learning_rate": 3.332734415076886e-05,
"loss": 3.5723,
"step": 1018368
},
{
"epoch": 1.01,
"learning_rate": 3.331895820325834e-05,
"loss": 3.5631,
"step": 1018880
},
{
"epoch": 1.01,
"learning_rate": 3.331057225574781e-05,
"loss": 3.5587,
"step": 1019392
},
{
"epoch": 1.01,
"learning_rate": 3.330218630823729e-05,
"loss": 3.5571,
"step": 1019904
},
{
"epoch": 1.01,
"learning_rate": 3.329381673953051e-05,
"loss": 3.5631,
"step": 1020416
},
{
"epoch": 1.01,
"learning_rate": 3.328543079201998e-05,
"loss": 3.5701,
"step": 1020928
},
{
"epoch": 1.01,
"learning_rate": 3.327704484450947e-05,
"loss": 3.555,
"step": 1021440
},
{
"epoch": 1.01,
"learning_rate": 3.326865889699895e-05,
"loss": 3.58,
"step": 1021952
},
{
"epoch": 1.01,
"learning_rate": 3.326027294948843e-05,
"loss": 3.5672,
"step": 1022464
},
{
"epoch": 1.01,
"learning_rate": 3.3251903380781636e-05,
"loss": 3.5477,
"step": 1022976
},
{
"epoch": 1.01,
"learning_rate": 3.3243517433271116e-05,
"loss": 3.5703,
"step": 1023488
},
{
"epoch": 1.01,
"learning_rate": 3.3235131485760596e-05,
"loss": 3.558,
"step": 1024000
},
{
"epoch": 1.01,
"learning_rate": 3.3226745538250076e-05,
"loss": 3.5629,
"step": 1024512
},
{
"epoch": 1.01,
"learning_rate": 3.3218359590739556e-05,
"loss": 3.5562,
"step": 1025024
},
{
"epoch": 1.01,
"learning_rate": 3.3209990022032765e-05,
"loss": 3.572,
"step": 1025536
},
{
"epoch": 1.01,
"learning_rate": 3.3201604074522245e-05,
"loss": 3.5542,
"step": 1026048
},
{
"epoch": 1.01,
"learning_rate": 3.3193218127011725e-05,
"loss": 3.5687,
"step": 1026560
},
{
"epoch": 1.01,
"learning_rate": 3.3184832179501205e-05,
"loss": 3.5489,
"step": 1027072
},
{
"epoch": 1.01,
"learning_rate": 3.317646261079442e-05,
"loss": 3.5629,
"step": 1027584
},
{
"epoch": 1.01,
"learning_rate": 3.31680766632839e-05,
"loss": 3.567,
"step": 1028096
},
{
"epoch": 1.01,
"learning_rate": 3.315969071577338e-05,
"loss": 3.5728,
"step": 1028608
},
{
"epoch": 1.01,
"learning_rate": 3.315130476826286e-05,
"loss": 3.568,
"step": 1029120
},
{
"epoch": 1.01,
"learning_rate": 3.314291882075234e-05,
"loss": 3.5671,
"step": 1029632
},
{
"epoch": 1.01,
"learning_rate": 3.313454925204555e-05,
"loss": 3.5835,
"step": 1030144
},
{
"epoch": 1.01,
"learning_rate": 3.312616330453503e-05,
"loss": 3.5612,
"step": 1030656
},
{
"epoch": 1.01,
"learning_rate": 3.311777735702451e-05,
"loss": 3.5735,
"step": 1031168
},
{
"epoch": 1.01,
"learning_rate": 3.310939140951399e-05,
"loss": 3.5647,
"step": 1031680
},
{
"epoch": 1.01,
"learning_rate": 3.310100546200347e-05,
"loss": 3.5667,
"step": 1032192
},
{
"epoch": 1.01,
"learning_rate": 3.309263589329668e-05,
"loss": 3.5621,
"step": 1032704
},
{
"epoch": 1.01,
"learning_rate": 3.308424994578616e-05,
"loss": 3.5699,
"step": 1033216
},
{
"epoch": 1.01,
"learning_rate": 3.307586399827564e-05,
"loss": 3.5716,
"step": 1033728
},
{
"epoch": 1.01,
"learning_rate": 3.306747805076512e-05,
"loss": 3.5769,
"step": 1034240
},
{
"epoch": 1.01,
"learning_rate": 3.3059108482058334e-05,
"loss": 3.5627,
"step": 1034752
},
{
"epoch": 1.01,
"learning_rate": 3.3050722534547814e-05,
"loss": 3.5502,
"step": 1035264
},
{
"epoch": 1.01,
"learning_rate": 3.3042336587037294e-05,
"loss": 3.5621,
"step": 1035776
},
{
"epoch": 1.01,
"learning_rate": 3.3033950639526774e-05,
"loss": 3.568,
"step": 1036288
},
{
"epoch": 1.01,
"learning_rate": 3.302558107081998e-05,
"loss": 3.5645,
"step": 1036800
},
{
"epoch": 1.01,
"learning_rate": 3.301719512330946e-05,
"loss": 3.5714,
"step": 1037312
},
{
"epoch": 1.01,
"learning_rate": 3.300880917579894e-05,
"loss": 3.562,
"step": 1037824
},
{
"epoch": 1.02,
"learning_rate": 3.300042322828842e-05,
"loss": 3.555,
"step": 1038336
},
{
"epoch": 1.02,
"learning_rate": 3.299205365958163e-05,
"loss": 3.5607,
"step": 1038848
},
{
"epoch": 1.02,
"learning_rate": 3.298366771207111e-05,
"loss": 3.5595,
"step": 1039360
},
{
"epoch": 1.02,
"learning_rate": 3.297528176456059e-05,
"loss": 3.5755,
"step": 1039872
},
{
"epoch": 1.02,
"learning_rate": 3.296689581705007e-05,
"loss": 3.5704,
"step": 1040384
},
{
"epoch": 1.02,
"learning_rate": 3.295852624834329e-05,
"loss": 3.5796,
"step": 1040896
},
{
"epoch": 1.02,
"learning_rate": 3.295014030083277e-05,
"loss": 3.556,
"step": 1041408
},
{
"epoch": 1.02,
"learning_rate": 3.294175435332225e-05,
"loss": 3.5614,
"step": 1041920
},
{
"epoch": 1.02,
"learning_rate": 3.293336840581173e-05,
"loss": 3.5652,
"step": 1042432
},
{
"epoch": 1.02,
"learning_rate": 3.292498245830121e-05,
"loss": 3.5637,
"step": 1042944
},
{
"epoch": 1.02,
"learning_rate": 3.291661288959442e-05,
"loss": 3.571,
"step": 1043456
},
{
"epoch": 1.02,
"learning_rate": 3.29082269420839e-05,
"loss": 3.5643,
"step": 1043968
},
{
"epoch": 1.02,
"learning_rate": 3.289984099457338e-05,
"loss": 3.5653,
"step": 1044480
},
{
"epoch": 1.02,
"learning_rate": 3.289145504706286e-05,
"loss": 3.5591,
"step": 1044992
},
{
"epoch": 1.02,
"learning_rate": 3.2883085478356066e-05,
"loss": 3.5738,
"step": 1045504
},
{
"epoch": 1.02,
"learning_rate": 3.2874699530845546e-05,
"loss": 3.5472,
"step": 1046016
},
{
"epoch": 1.02,
"learning_rate": 3.2866313583335026e-05,
"loss": 3.5573,
"step": 1046528
},
{
"epoch": 1.02,
"learning_rate": 3.285792763582451e-05,
"loss": 3.564,
"step": 1047040
},
{
"epoch": 1.02,
"learning_rate": 3.284955806711772e-05,
"loss": 3.5657,
"step": 1047552
},
{
"epoch": 1.02,
"learning_rate": 3.28411721196072e-05,
"loss": 3.5553,
"step": 1048064
},
{
"epoch": 1.02,
"learning_rate": 3.283278617209668e-05,
"loss": 3.5652,
"step": 1048576
},
{
"epoch": 1.02,
"learning_rate": 3.282440022458616e-05,
"loss": 3.544,
"step": 1049088
},
{
"epoch": 1.02,
"learning_rate": 3.281603065587937e-05,
"loss": 3.5714,
"step": 1049600
},
{
"epoch": 1.02,
"learning_rate": 3.280764470836885e-05,
"loss": 3.5608,
"step": 1050112
},
{
"epoch": 1.02,
"learning_rate": 3.279925876085833e-05,
"loss": 3.5658,
"step": 1050624
},
{
"epoch": 1.02,
"learning_rate": 3.279087281334781e-05,
"loss": 3.5726,
"step": 1051136
},
{
"epoch": 1.02,
"learning_rate": 3.278250324464102e-05,
"loss": 3.5759,
"step": 1051648
},
{
"epoch": 1.02,
"learning_rate": 3.27741172971305e-05,
"loss": 3.557,
"step": 1052160
},
{
"epoch": 1.02,
"learning_rate": 3.276573134961998e-05,
"loss": 3.5615,
"step": 1052672
},
{
"epoch": 1.02,
"learning_rate": 3.275734540210946e-05,
"loss": 3.5659,
"step": 1053184
},
{
"epoch": 1.02,
"learning_rate": 3.2748975833402675e-05,
"loss": 3.5605,
"step": 1053696
},
{
"epoch": 1.02,
"learning_rate": 3.2740589885892155e-05,
"loss": 3.563,
"step": 1054208
},
{
"epoch": 1.02,
"learning_rate": 3.2732203938381635e-05,
"loss": 3.5555,
"step": 1054720
},
{
"epoch": 1.02,
"learning_rate": 3.2723817990871115e-05,
"loss": 3.5634,
"step": 1055232
},
{
"epoch": 1.02,
"learning_rate": 3.2715448422164324e-05,
"loss": 3.5571,
"step": 1055744
},
{
"epoch": 1.02,
"learning_rate": 3.2707062474653804e-05,
"loss": 3.5551,
"step": 1056256
},
{
"epoch": 1.02,
"learning_rate": 3.2698676527143284e-05,
"loss": 3.5597,
"step": 1056768
},
{
"epoch": 1.02,
"learning_rate": 3.2690290579632764e-05,
"loss": 3.5592,
"step": 1057280
},
{
"epoch": 1.02,
"learning_rate": 3.268190463212224e-05,
"loss": 3.5527,
"step": 1057792
},
{
"epoch": 1.02,
"learning_rate": 3.267353506341545e-05,
"loss": 3.5724,
"step": 1058304
},
{
"epoch": 1.02,
"learning_rate": 3.266514911590493e-05,
"loss": 3.5622,
"step": 1058816
},
{
"epoch": 1.02,
"learning_rate": 3.265676316839441e-05,
"loss": 3.5761,
"step": 1059328
},
{
"epoch": 1.02,
"learning_rate": 3.264837722088389e-05,
"loss": 3.5549,
"step": 1059840
},
{
"epoch": 1.02,
"learning_rate": 3.264000765217711e-05,
"loss": 3.5668,
"step": 1060352
},
{
"epoch": 1.02,
"learning_rate": 3.263162170466659e-05,
"loss": 3.5674,
"step": 1060864
},
{
"epoch": 1.02,
"learning_rate": 3.262323575715606e-05,
"loss": 3.5641,
"step": 1061376
},
{
"epoch": 1.02,
"learning_rate": 3.261484980964554e-05,
"loss": 3.5594,
"step": 1061888
},
{
"epoch": 1.02,
"learning_rate": 3.260646386213502e-05,
"loss": 3.5614,
"step": 1062400
},
{
"epoch": 1.02,
"learning_rate": 3.259809429342824e-05,
"loss": 3.5695,
"step": 1062912
},
{
"epoch": 1.02,
"learning_rate": 3.258970834591771e-05,
"loss": 3.571,
"step": 1063424
},
{
"epoch": 1.02,
"learning_rate": 3.258132239840719e-05,
"loss": 3.562,
"step": 1063936
},
{
"epoch": 1.02,
"learning_rate": 3.257293645089667e-05,
"loss": 3.561,
"step": 1064448
},
{
"epoch": 1.02,
"learning_rate": 3.256456688218989e-05,
"loss": 3.5652,
"step": 1064960
},
{
"epoch": 1.02,
"learning_rate": 3.255618093467937e-05,
"loss": 3.5612,
"step": 1065472
},
{
"epoch": 1.02,
"learning_rate": 3.254779498716885e-05,
"loss": 3.5561,
"step": 1065984
},
{
"epoch": 1.02,
"learning_rate": 3.253940903965833e-05,
"loss": 3.5679,
"step": 1066496
},
{
"epoch": 1.02,
"learning_rate": 3.253102309214781e-05,
"loss": 3.5607,
"step": 1067008
},
{
"epoch": 1.02,
"learning_rate": 3.2522653523441016e-05,
"loss": 3.5665,
"step": 1067520
},
{
"epoch": 1.02,
"learning_rate": 3.2514267575930496e-05,
"loss": 3.5528,
"step": 1068032
},
{
"epoch": 1.03,
"eval_loss": 3.8441240787506104,
"eval_runtime": 336.2463,
"eval_samples_per_second": 1134.856,
"eval_steps_per_second": 35.465,
"step": 1068480
},
{
"epoch": 0.0,
"learning_rate": 3.2505881628419976e-05,
"loss": 3.5725,
"step": 1068544
},
{
"epoch": 0.0,
"learning_rate": 3.2497495680909456e-05,
"loss": 3.5514,
"step": 1069056
},
{
"epoch": 0.0,
"learning_rate": 3.2489109733398936e-05,
"loss": 3.5524,
"step": 1069568
},
{
"epoch": 0.0,
"learning_rate": 3.2480723785888416e-05,
"loss": 3.5663,
"step": 1070080
},
{
"epoch": 0.0,
"learning_rate": 3.2472337838377895e-05,
"loss": 3.5683,
"step": 1070592
},
{
"epoch": 0.0,
"learning_rate": 3.2463968269671105e-05,
"loss": 3.561,
"step": 1071104
},
{
"epoch": 0.0,
"learning_rate": 3.245558232216059e-05,
"loss": 3.5549,
"step": 1071616
},
{
"epoch": 0.0,
"learning_rate": 3.244719637465007e-05,
"loss": 3.5551,
"step": 1072128
},
{
"epoch": 0.0,
"learning_rate": 3.243881042713955e-05,
"loss": 3.5481,
"step": 1072640
},
{
"epoch": 0.0,
"learning_rate": 3.243044085843276e-05,
"loss": 3.5669,
"step": 1073152
},
{
"epoch": 0.0,
"learning_rate": 3.242205491092224e-05,
"loss": 3.5571,
"step": 1073664
},
{
"epoch": 0.0,
"learning_rate": 3.241366896341172e-05,
"loss": 3.5642,
"step": 1074176
},
{
"epoch": 0.0,
"learning_rate": 3.24052830159012e-05,
"loss": 3.5611,
"step": 1074688
},
{
"epoch": 0.0,
"learning_rate": 3.239691344719441e-05,
"loss": 3.5479,
"step": 1075200
},
{
"epoch": 0.0,
"learning_rate": 3.238852749968389e-05,
"loss": 3.5537,
"step": 1075712
},
{
"epoch": 0.0,
"learning_rate": 3.238014155217337e-05,
"loss": 3.5464,
"step": 1076224
},
{
"epoch": 0.0,
"learning_rate": 3.237175560466285e-05,
"loss": 3.5572,
"step": 1076736
},
{
"epoch": 0.0,
"learning_rate": 3.236338603595606e-05,
"loss": 3.5512,
"step": 1077248
},
{
"epoch": 0.0,
"learning_rate": 3.2355000088445545e-05,
"loss": 3.5544,
"step": 1077760
},
{
"epoch": 0.0,
"learning_rate": 3.2346614140935025e-05,
"loss": 3.5541,
"step": 1078272
},
{
"epoch": 0.0,
"learning_rate": 3.2338228193424505e-05,
"loss": 3.5639,
"step": 1078784
},
{
"epoch": 0.0,
"learning_rate": 3.2329858624717714e-05,
"loss": 3.5641,
"step": 1079296
},
{
"epoch": 0.0,
"learning_rate": 3.2321472677207194e-05,
"loss": 3.5603,
"step": 1079808
},
{
"epoch": 0.0,
"learning_rate": 3.2313086729696674e-05,
"loss": 3.5531,
"step": 1080320
},
{
"epoch": 0.0,
"learning_rate": 3.2304700782186154e-05,
"loss": 3.5632,
"step": 1080832
},
{
"epoch": 0.0,
"learning_rate": 3.229633121347936e-05,
"loss": 3.5549,
"step": 1081344
},
{
"epoch": 0.0,
"learning_rate": 3.228794526596884e-05,
"loss": 3.5522,
"step": 1081856
},
{
"epoch": 0.0,
"learning_rate": 3.227955931845832e-05,
"loss": 3.5634,
"step": 1082368
},
{
"epoch": 0.0,
"learning_rate": 3.22711733709478e-05,
"loss": 3.5454,
"step": 1082880
},
{
"epoch": 0.0,
"learning_rate": 3.226280380224101e-05,
"loss": 3.546,
"step": 1083392
},
{
"epoch": 0.01,
"learning_rate": 3.22544178547305e-05,
"loss": 3.5506,
"step": 1083904
},
{
"epoch": 0.01,
"learning_rate": 3.224603190721998e-05,
"loss": 3.5501,
"step": 1084416
},
{
"epoch": 0.01,
"learning_rate": 3.223764595970946e-05,
"loss": 3.5641,
"step": 1084928
},
{
"epoch": 0.01,
"learning_rate": 3.222926001219894e-05,
"loss": 3.5632,
"step": 1085440
},
{
"epoch": 0.01,
"learning_rate": 3.222089044349215e-05,
"loss": 3.5471,
"step": 1085952
},
{
"epoch": 0.01,
"learning_rate": 3.221250449598163e-05,
"loss": 3.5619,
"step": 1086464
},
{
"epoch": 0.01,
"learning_rate": 3.220411854847111e-05,
"loss": 3.5621,
"step": 1086976
},
{
"epoch": 0.01,
"learning_rate": 3.219573260096059e-05,
"loss": 3.5454,
"step": 1087488
},
{
"epoch": 0.01,
"learning_rate": 3.2187363032253797e-05,
"loss": 3.5507,
"step": 1088000
},
{
"epoch": 0.01,
"learning_rate": 3.2178977084743277e-05,
"loss": 3.5471,
"step": 1088512
},
{
"epoch": 0.01,
"learning_rate": 3.2170591137232756e-05,
"loss": 3.5453,
"step": 1089024
},
{
"epoch": 0.01,
"learning_rate": 3.2162205189722236e-05,
"loss": 3.5542,
"step": 1089536
},
{
"epoch": 0.01,
"learning_rate": 3.2153819242211716e-05,
"loss": 3.5625,
"step": 1090048
},
{
"epoch": 0.01,
"learning_rate": 3.214544967350493e-05,
"loss": 3.5536,
"step": 1090560
},
{
"epoch": 0.01,
"learning_rate": 3.213706372599441e-05,
"loss": 3.5496,
"step": 1091072
},
{
"epoch": 0.01,
"learning_rate": 3.212867777848389e-05,
"loss": 3.557,
"step": 1091584
},
{
"epoch": 0.01,
"learning_rate": 3.212029183097337e-05,
"loss": 3.5481,
"step": 1092096
},
{
"epoch": 0.01,
"learning_rate": 3.211192226226658e-05,
"loss": 3.5465,
"step": 1092608
},
{
"epoch": 0.01,
"learning_rate": 3.210353631475606e-05,
"loss": 3.5297,
"step": 1093120
},
{
"epoch": 0.01,
"learning_rate": 3.209515036724554e-05,
"loss": 3.5588,
"step": 1093632
},
{
"epoch": 0.01,
"learning_rate": 3.208676441973502e-05,
"loss": 3.5515,
"step": 1094144
},
{
"epoch": 0.01,
"learning_rate": 3.207839485102823e-05,
"loss": 3.5567,
"step": 1094656
},
{
"epoch": 0.01,
"learning_rate": 3.207000890351771e-05,
"loss": 3.5474,
"step": 1095168
},
{
"epoch": 0.01,
"learning_rate": 3.206162295600719e-05,
"loss": 3.5401,
"step": 1095680
},
{
"epoch": 0.01,
"learning_rate": 3.205323700849667e-05,
"loss": 3.5445,
"step": 1096192
},
{
"epoch": 0.01,
"learning_rate": 3.204485106098615e-05,
"loss": 3.5495,
"step": 1096704
},
{
"epoch": 0.01,
"learning_rate": 3.2036481492279366e-05,
"loss": 3.5538,
"step": 1097216
},
{
"epoch": 0.01,
"learning_rate": 3.2028095544768846e-05,
"loss": 3.537,
"step": 1097728
},
{
"epoch": 0.01,
"learning_rate": 3.201970959725832e-05,
"loss": 3.5631,
"step": 1098240
},
{
"epoch": 0.01,
"learning_rate": 3.20113236497478e-05,
"loss": 3.5491,
"step": 1098752
},
{
"epoch": 0.01,
"learning_rate": 3.2002954081041015e-05,
"loss": 3.5371,
"step": 1099264
},
{
"epoch": 0.01,
"learning_rate": 3.1994568133530495e-05,
"loss": 3.5563,
"step": 1099776
},
{
"epoch": 0.01,
"learning_rate": 3.198618218601997e-05,
"loss": 3.544,
"step": 1100288
},
{
"epoch": 0.01,
"learning_rate": 3.197779623850945e-05,
"loss": 3.5469,
"step": 1100800
},
{
"epoch": 0.01,
"learning_rate": 3.196941029099893e-05,
"loss": 3.5399,
"step": 1101312
},
{
"epoch": 0.01,
"learning_rate": 3.1961040722292144e-05,
"loss": 3.5565,
"step": 1101824
},
{
"epoch": 0.01,
"learning_rate": 3.1952654774781624e-05,
"loss": 3.5425,
"step": 1102336
},
{
"epoch": 0.01,
"learning_rate": 3.1944268827271104e-05,
"loss": 3.5439,
"step": 1102848
},
{
"epoch": 0.01,
"learning_rate": 3.1935882879760584e-05,
"loss": 3.5406,
"step": 1103360
},
{
"epoch": 0.01,
"learning_rate": 3.192751331105379e-05,
"loss": 3.5434,
"step": 1103872
},
{
"epoch": 0.01,
"learning_rate": 3.191912736354327e-05,
"loss": 3.5485,
"step": 1104384
},
{
"epoch": 0.01,
"learning_rate": 3.191074141603275e-05,
"loss": 3.5615,
"step": 1104896
},
{
"epoch": 0.01,
"learning_rate": 3.190235546852223e-05,
"loss": 3.551,
"step": 1105408
},
{
"epoch": 0.01,
"learning_rate": 3.189398589981544e-05,
"loss": 3.5506,
"step": 1105920
},
{
"epoch": 0.01,
"learning_rate": 3.188559995230492e-05,
"loss": 3.5667,
"step": 1106432
},
{
"epoch": 0.01,
"learning_rate": 3.18772140047944e-05,
"loss": 3.5456,
"step": 1106944
},
{
"epoch": 0.01,
"learning_rate": 3.186882805728388e-05,
"loss": 3.5544,
"step": 1107456
},
{
"epoch": 0.01,
"learning_rate": 3.186045848857709e-05,
"loss": 3.5516,
"step": 1107968
},
{
"epoch": 0.01,
"learning_rate": 3.185207254106658e-05,
"loss": 3.5551,
"step": 1108480
},
{
"epoch": 0.01,
"learning_rate": 3.184368659355606e-05,
"loss": 3.5459,
"step": 1108992
},
{
"epoch": 0.01,
"learning_rate": 3.183530064604554e-05,
"loss": 3.5524,
"step": 1109504
},
{
"epoch": 0.01,
"learning_rate": 3.1826931077338746e-05,
"loss": 3.5559,
"step": 1110016
},
{
"epoch": 0.01,
"learning_rate": 3.1818545129828226e-05,
"loss": 3.5618,
"step": 1110528
},
{
"epoch": 0.01,
"learning_rate": 3.1810159182317706e-05,
"loss": 3.547,
"step": 1111040
},
{
"epoch": 0.01,
"learning_rate": 3.1801773234807186e-05,
"loss": 3.5324,
"step": 1111552
},
{
"epoch": 0.01,
"learning_rate": 3.1793403666100395e-05,
"loss": 3.5447,
"step": 1112064
},
{
"epoch": 0.01,
"learning_rate": 3.1785017718589875e-05,
"loss": 3.5554,
"step": 1112576
},
{
"epoch": 0.01,
"learning_rate": 3.1776631771079355e-05,
"loss": 3.5517,
"step": 1113088
},
{
"epoch": 0.01,
"learning_rate": 3.1768245823568835e-05,
"loss": 3.5538,
"step": 1113600
},
{
"epoch": 0.01,
"learning_rate": 3.1759876254862044e-05,
"loss": 3.5478,
"step": 1114112
},
{
"epoch": 0.02,
"learning_rate": 3.175149030735153e-05,
"loss": 3.5395,
"step": 1114624
},
{
"epoch": 0.02,
"learning_rate": 3.174310435984101e-05,
"loss": 3.5433,
"step": 1115136
},
{
"epoch": 0.02,
"learning_rate": 3.173471841233049e-05,
"loss": 3.5456,
"step": 1115648
},
{
"epoch": 0.02,
"learning_rate": 3.17263488436237e-05,
"loss": 3.557,
"step": 1116160
},
{
"epoch": 0.02,
"learning_rate": 3.171796289611318e-05,
"loss": 3.5547,
"step": 1116672
},
{
"epoch": 0.02,
"learning_rate": 3.170957694860266e-05,
"loss": 3.5679,
"step": 1117184
},
{
"epoch": 0.02,
"learning_rate": 3.170119100109214e-05,
"loss": 3.5369,
"step": 1117696
},
{
"epoch": 0.02,
"learning_rate": 3.169282143238535e-05,
"loss": 3.5444,
"step": 1118208
},
{
"epoch": 0.02,
"learning_rate": 3.168443548487483e-05,
"loss": 3.5484,
"step": 1118720
},
{
"epoch": 0.02,
"learning_rate": 3.167604953736431e-05,
"loss": 3.5511,
"step": 1119232
},
{
"epoch": 0.02,
"learning_rate": 3.166766358985379e-05,
"loss": 3.5533,
"step": 1119744
},
{
"epoch": 0.02,
"learning_rate": 3.165927764234327e-05,
"loss": 3.5496,
"step": 1120256
},
{
"epoch": 0.02,
"learning_rate": 3.165089169483275e-05,
"loss": 3.549,
"step": 1120768
},
{
"epoch": 0.02,
"learning_rate": 3.1642522126125965e-05,
"loss": 3.5405,
"step": 1121280
},
{
"epoch": 0.02,
"learning_rate": 3.1634136178615445e-05,
"loss": 3.5555,
"step": 1121792
},
{
"epoch": 0.02,
"learning_rate": 3.1625750231104925e-05,
"loss": 3.5309,
"step": 1122304
},
{
"epoch": 0.02,
"learning_rate": 3.1617364283594405e-05,
"loss": 3.5421,
"step": 1122816
},
{
"epoch": 0.02,
"learning_rate": 3.1608994714887614e-05,
"loss": 3.5497,
"step": 1123328
},
{
"epoch": 0.02,
"learning_rate": 3.1600608767377094e-05,
"loss": 3.5515,
"step": 1123840
},
{
"epoch": 0.02,
"learning_rate": 3.1592222819866574e-05,
"loss": 3.5414,
"step": 1124352
},
{
"epoch": 0.02,
"learning_rate": 3.1583836872356054e-05,
"loss": 3.5432,
"step": 1124864
},
{
"epoch": 0.02,
"learning_rate": 3.1575450924845533e-05,
"loss": 3.5379,
"step": 1125376
},
{
"epoch": 0.02,
"learning_rate": 3.156708135613874e-05,
"loss": 3.5488,
"step": 1125888
},
{
"epoch": 0.02,
"learning_rate": 3.155869540862822e-05,
"loss": 3.5447,
"step": 1126400
},
{
"epoch": 0.02,
"learning_rate": 3.15503094611177e-05,
"loss": 3.5524,
"step": 1126912
},
{
"epoch": 0.02,
"learning_rate": 3.154192351360718e-05,
"loss": 3.5569,
"step": 1127424
},
{
"epoch": 0.02,
"learning_rate": 3.15335539449004e-05,
"loss": 3.558,
"step": 1127936
},
{
"epoch": 0.02,
"learning_rate": 3.152516799738988e-05,
"loss": 3.539,
"step": 1128448
},
{
"epoch": 0.02,
"learning_rate": 3.151678204987936e-05,
"loss": 3.5461,
"step": 1128960
},
{
"epoch": 0.02,
"learning_rate": 3.150839610236884e-05,
"loss": 3.5518,
"step": 1129472
},
{
"epoch": 0.02,
"learning_rate": 3.150001015485832e-05,
"loss": 3.5476,
"step": 1129984
},
{
"epoch": 0.02,
"learning_rate": 3.149164058615153e-05,
"loss": 3.545,
"step": 1130496
},
{
"epoch": 0.02,
"learning_rate": 3.148325463864101e-05,
"loss": 3.5441,
"step": 1131008
},
{
"epoch": 0.02,
"learning_rate": 3.147486869113049e-05,
"loss": 3.5443,
"step": 1131520
},
{
"epoch": 0.02,
"learning_rate": 3.146648274361997e-05,
"loss": 3.5447,
"step": 1132032
},
{
"epoch": 0.02,
"learning_rate": 3.145809679610945e-05,
"loss": 3.5374,
"step": 1132544
},
{
"epoch": 0.02,
"learning_rate": 3.1449727227402656e-05,
"loss": 3.5462,
"step": 1133056
},
{
"epoch": 0.02,
"learning_rate": 3.1441341279892136e-05,
"loss": 3.5446,
"step": 1133568
},
{
"epoch": 0.02,
"learning_rate": 3.143295533238162e-05,
"loss": 3.5382,
"step": 1134080
},
{
"epoch": 0.02,
"learning_rate": 3.14245693848711e-05,
"loss": 3.5502,
"step": 1134592
},
{
"epoch": 0.02,
"learning_rate": 3.141619981616431e-05,
"loss": 3.5507,
"step": 1135104
},
{
"epoch": 0.02,
"learning_rate": 3.140781386865379e-05,
"loss": 3.5587,
"step": 1135616
},
{
"epoch": 0.02,
"learning_rate": 3.139942792114327e-05,
"loss": 3.5448,
"step": 1136128
},
{
"epoch": 0.02,
"learning_rate": 3.1391041973632745e-05,
"loss": 3.5474,
"step": 1136640
},
{
"epoch": 0.02,
"learning_rate": 3.138267240492596e-05,
"loss": 3.5553,
"step": 1137152
},
{
"epoch": 0.02,
"learning_rate": 3.137428645741544e-05,
"loss": 3.5448,
"step": 1137664
},
{
"epoch": 0.02,
"learning_rate": 3.136590050990492e-05,
"loss": 3.5496,
"step": 1138176
},
{
"epoch": 0.02,
"learning_rate": 3.1357514562394394e-05,
"loss": 3.5477,
"step": 1138688
},
{
"epoch": 0.02,
"learning_rate": 3.1349128614883874e-05,
"loss": 3.553,
"step": 1139200
},
{
"epoch": 0.02,
"learning_rate": 3.134075904617709e-05,
"loss": 3.5529,
"step": 1139712
},
{
"epoch": 0.02,
"learning_rate": 3.133237309866657e-05,
"loss": 3.549,
"step": 1140224
},
{
"epoch": 0.02,
"learning_rate": 3.132398715115605e-05,
"loss": 3.5447,
"step": 1140736
},
{
"epoch": 0.02,
"learning_rate": 3.131560120364553e-05,
"loss": 3.5489,
"step": 1141248
},
{
"epoch": 0.02,
"learning_rate": 3.1307231634938745e-05,
"loss": 3.5429,
"step": 1141760
},
{
"epoch": 0.02,
"learning_rate": 3.129884568742822e-05,
"loss": 3.5416,
"step": 1142272
},
{
"epoch": 0.02,
"learning_rate": 3.12904597399177e-05,
"loss": 3.5498,
"step": 1142784
},
{
"epoch": 0.02,
"learning_rate": 3.128207379240718e-05,
"loss": 3.5404,
"step": 1143296
},
{
"epoch": 0.02,
"learning_rate": 3.1273704223700394e-05,
"loss": 3.5594,
"step": 1143808
},
{
"epoch": 0.02,
"learning_rate": 3.126531827618987e-05,
"loss": 3.5343,
"step": 1144320
},
{
"epoch": 0.03,
"eval_loss": 3.8445253372192383,
"eval_runtime": 304.4441,
"eval_samples_per_second": 1253.403,
"eval_steps_per_second": 39.17,
"step": 1144800
},
{
"epoch": 1.0,
"learning_rate": 3.125693232867935e-05,
"loss": 3.5428,
"step": 1144832
},
{
"epoch": 1.0,
"learning_rate": 3.124854638116883e-05,
"loss": 3.5407,
"step": 1145344
},
{
"epoch": 1.0,
"learning_rate": 3.1240176812462043e-05,
"loss": 3.537,
"step": 1145856
},
{
"epoch": 1.0,
"learning_rate": 3.123179086495152e-05,
"loss": 3.5512,
"step": 1146368
},
{
"epoch": 1.0,
"learning_rate": 3.1223404917441e-05,
"loss": 3.5528,
"step": 1146880
},
{
"epoch": 1.0,
"learning_rate": 3.121501896993048e-05,
"loss": 3.5477,
"step": 1147392
},
{
"epoch": 1.0,
"learning_rate": 3.120663302241996e-05,
"loss": 3.5365,
"step": 1147904
},
{
"epoch": 1.0,
"learning_rate": 3.119824707490944e-05,
"loss": 3.5392,
"step": 1148416
},
{
"epoch": 1.0,
"learning_rate": 3.118987750620265e-05,
"loss": 3.5377,
"step": 1148928
},
{
"epoch": 1.0,
"learning_rate": 3.118149155869213e-05,
"loss": 3.5486,
"step": 1149440
},
{
"epoch": 1.0,
"learning_rate": 3.117310561118161e-05,
"loss": 3.5413,
"step": 1149952
},
{
"epoch": 1.0,
"learning_rate": 3.116471966367109e-05,
"loss": 3.5477,
"step": 1150464
},
{
"epoch": 1.0,
"learning_rate": 3.11563500949643e-05,
"loss": 3.5453,
"step": 1150976
},
{
"epoch": 1.0,
"learning_rate": 3.114796414745378e-05,
"loss": 3.5332,
"step": 1151488
},
{
"epoch": 1.0,
"learning_rate": 3.113957819994326e-05,
"loss": 3.538,
"step": 1152000
},
{
"epoch": 1.0,
"learning_rate": 3.113119225243275e-05,
"loss": 3.531,
"step": 1152512
},
{
"epoch": 1.0,
"learning_rate": 3.112282268372596e-05,
"loss": 3.5423,
"step": 1153024
},
{
"epoch": 1.0,
"learning_rate": 3.111443673621544e-05,
"loss": 3.5351,
"step": 1153536
},
{
"epoch": 1.0,
"learning_rate": 3.110605078870492e-05,
"loss": 3.5393,
"step": 1154048
},
{
"epoch": 1.0,
"learning_rate": 3.10976648411944e-05,
"loss": 3.5386,
"step": 1154560
},
{
"epoch": 1.0,
"learning_rate": 3.108927889368388e-05,
"loss": 3.5494,
"step": 1155072
},
{
"epoch": 1.0,
"learning_rate": 3.1080909324977086e-05,
"loss": 3.5468,
"step": 1155584
},
{
"epoch": 1.0,
"learning_rate": 3.1072523377466566e-05,
"loss": 3.5426,
"step": 1156096
},
{
"epoch": 1.0,
"learning_rate": 3.1064137429956046e-05,
"loss": 3.5418,
"step": 1156608
},
{
"epoch": 1.0,
"learning_rate": 3.1055751482445526e-05,
"loss": 3.5472,
"step": 1157120
},
{
"epoch": 1.0,
"learning_rate": 3.1047381913738735e-05,
"loss": 3.543,
"step": 1157632
},
{
"epoch": 1.0,
"learning_rate": 3.1038995966228215e-05,
"loss": 3.5357,
"step": 1158144
},
{
"epoch": 1.0,
"learning_rate": 3.10306100187177e-05,
"loss": 3.5448,
"step": 1158656
},
{
"epoch": 1.0,
"learning_rate": 3.102222407120718e-05,
"loss": 3.5294,
"step": 1159168
},
{
"epoch": 1.0,
"learning_rate": 3.101385450250039e-05,
"loss": 3.5322,
"step": 1159680
},
{
"epoch": 1.01,
"learning_rate": 3.100546855498987e-05,
"loss": 3.535,
"step": 1160192
},
{
"epoch": 1.01,
"learning_rate": 3.099708260747935e-05,
"loss": 3.5372,
"step": 1160704
},
{
"epoch": 1.01,
"learning_rate": 3.098869665996883e-05,
"loss": 3.547,
"step": 1161216
},
{
"epoch": 1.01,
"learning_rate": 3.098031071245831e-05,
"loss": 3.5442,
"step": 1161728
},
{
"epoch": 1.01,
"learning_rate": 3.097194114375152e-05,
"loss": 3.5381,
"step": 1162240
},
{
"epoch": 1.01,
"learning_rate": 3.0963555196241e-05,
"loss": 3.5431,
"step": 1162752
},
{
"epoch": 1.01,
"learning_rate": 3.095516924873048e-05,
"loss": 3.5508,
"step": 1163264
},
{
"epoch": 1.01,
"learning_rate": 3.094678330121996e-05,
"loss": 3.5301,
"step": 1163776
},
{
"epoch": 1.01,
"learning_rate": 3.093841373251317e-05,
"loss": 3.5391,
"step": 1164288
},
{
"epoch": 1.01,
"learning_rate": 3.0930027785002655e-05,
"loss": 3.5258,
"step": 1164800
},
{
"epoch": 1.01,
"learning_rate": 3.0921641837492135e-05,
"loss": 3.5343,
"step": 1165312
},
{
"epoch": 1.01,
"learning_rate": 3.0913255889981615e-05,
"loss": 3.5351,
"step": 1165824
},
{
"epoch": 1.01,
"learning_rate": 3.0904869942471095e-05,
"loss": 3.5462,
"step": 1166336
},
{
"epoch": 1.01,
"learning_rate": 3.0896500373764304e-05,
"loss": 3.5395,
"step": 1166848
},
{
"epoch": 1.01,
"learning_rate": 3.0888114426253784e-05,
"loss": 3.5329,
"step": 1167360
},
{
"epoch": 1.01,
"learning_rate": 3.0879728478743264e-05,
"loss": 3.5444,
"step": 1167872
},
{
"epoch": 1.01,
"learning_rate": 3.0871342531232744e-05,
"loss": 3.534,
"step": 1168384
},
{
"epoch": 1.01,
"learning_rate": 3.086297296252595e-05,
"loss": 3.5315,
"step": 1168896
},
{
"epoch": 1.01,
"learning_rate": 3.085458701501543e-05,
"loss": 3.514,
"step": 1169408
},
{
"epoch": 1.01,
"learning_rate": 3.084620106750491e-05,
"loss": 3.543,
"step": 1169920
},
{
"epoch": 1.01,
"learning_rate": 3.083781511999439e-05,
"loss": 3.5357,
"step": 1170432
},
{
"epoch": 1.01,
"learning_rate": 3.082942917248387e-05,
"loss": 3.5409,
"step": 1170944
},
{
"epoch": 1.01,
"learning_rate": 3.082105960377709e-05,
"loss": 3.5329,
"step": 1171456
},
{
"epoch": 1.01,
"learning_rate": 3.081267365626657e-05,
"loss": 3.527,
"step": 1171968
},
{
"epoch": 1.01,
"learning_rate": 3.080428770875605e-05,
"loss": 3.5277,
"step": 1172480
},
{
"epoch": 1.01,
"learning_rate": 3.079590176124553e-05,
"loss": 3.5282,
"step": 1172992
},
{
"epoch": 1.01,
"learning_rate": 3.078753219253874e-05,
"loss": 3.542,
"step": 1173504
},
{
"epoch": 1.01,
"learning_rate": 3.077914624502822e-05,
"loss": 3.5273,
"step": 1174016
},
{
"epoch": 1.01,
"learning_rate": 3.07707602975177e-05,
"loss": 3.5419,
"step": 1174528
},
{
"epoch": 1.01,
"learning_rate": 3.076237435000718e-05,
"loss": 3.5341,
"step": 1175040
},
{
"epoch": 1.01,
"learning_rate": 3.075400478130039e-05,
"loss": 3.5257,
"step": 1175552
},
{
"epoch": 1.01,
"learning_rate": 3.074561883378987e-05,
"loss": 3.5381,
"step": 1176064
},
{
"epoch": 1.01,
"learning_rate": 3.073723288627935e-05,
"loss": 3.5318,
"step": 1176576
},
{
"epoch": 1.01,
"learning_rate": 3.072884693876883e-05,
"loss": 3.5305,
"step": 1177088
},
{
"epoch": 1.01,
"learning_rate": 3.0720460991258307e-05,
"loss": 3.5243,
"step": 1177600
},
{
"epoch": 1.01,
"learning_rate": 3.071209142255152e-05,
"loss": 3.5411,
"step": 1178112
},
{
"epoch": 1.01,
"learning_rate": 3.0703705475041e-05,
"loss": 3.5278,
"step": 1178624
},
{
"epoch": 1.01,
"learning_rate": 3.0695319527530476e-05,
"loss": 3.5301,
"step": 1179136
},
{
"epoch": 1.01,
"learning_rate": 3.0686933580019956e-05,
"loss": 3.5204,
"step": 1179648
},
{
"epoch": 1.01,
"learning_rate": 3.0678547632509436e-05,
"loss": 3.5311,
"step": 1180160
},
{
"epoch": 1.01,
"learning_rate": 3.0670178063802645e-05,
"loss": 3.5315,
"step": 1180672
},
{
"epoch": 1.01,
"learning_rate": 3.0661792116292125e-05,
"loss": 3.5451,
"step": 1181184
},
{
"epoch": 1.01,
"learning_rate": 3.0653406168781605e-05,
"loss": 3.5331,
"step": 1181696
},
{
"epoch": 1.01,
"learning_rate": 3.0645020221271084e-05,
"loss": 3.5398,
"step": 1182208
},
{
"epoch": 1.01,
"learning_rate": 3.0636634273760564e-05,
"loss": 3.5449,
"step": 1182720
},
{
"epoch": 1.01,
"learning_rate": 3.062826470505378e-05,
"loss": 3.5369,
"step": 1183232
},
{
"epoch": 1.01,
"learning_rate": 3.061987875754326e-05,
"loss": 3.5331,
"step": 1183744
},
{
"epoch": 1.01,
"learning_rate": 3.061149281003274e-05,
"loss": 3.5385,
"step": 1184256
},
{
"epoch": 1.01,
"learning_rate": 3.060310686252222e-05,
"loss": 3.5393,
"step": 1184768
},
{
"epoch": 1.01,
"learning_rate": 3.059473729381543e-05,
"loss": 3.5328,
"step": 1185280
},
{
"epoch": 1.01,
"learning_rate": 3.058635134630491e-05,
"loss": 3.5366,
"step": 1185792
},
{
"epoch": 1.01,
"learning_rate": 3.057796539879439e-05,
"loss": 3.5455,
"step": 1186304
},
{
"epoch": 1.01,
"learning_rate": 3.056957945128387e-05,
"loss": 3.5463,
"step": 1186816
},
{
"epoch": 1.01,
"learning_rate": 3.056120988257708e-05,
"loss": 3.5331,
"step": 1187328
},
{
"epoch": 1.01,
"learning_rate": 3.055282393506656e-05,
"loss": 3.5155,
"step": 1187840
},
{
"epoch": 1.01,
"learning_rate": 3.054443798755604e-05,
"loss": 3.5277,
"step": 1188352
},
{
"epoch": 1.01,
"learning_rate": 3.053605204004552e-05,
"loss": 3.5398,
"step": 1188864
},
{
"epoch": 1.01,
"learning_rate": 3.0527666092535e-05,
"loss": 3.5352,
"step": 1189376
},
{
"epoch": 1.01,
"learning_rate": 3.051928014502448e-05,
"loss": 3.5409,
"step": 1189888
},
{
"epoch": 1.01,
"learning_rate": 3.051091057631769e-05,
"loss": 3.5343,
"step": 1190400
},
{
"epoch": 1.02,
"learning_rate": 3.050252462880717e-05,
"loss": 3.5259,
"step": 1190912
},
{
"epoch": 1.02,
"learning_rate": 3.0494138681296654e-05,
"loss": 3.5237,
"step": 1191424
},
{
"epoch": 1.02,
"learning_rate": 3.0485752733786134e-05,
"loss": 3.5303,
"step": 1191936
},
{
"epoch": 1.02,
"learning_rate": 3.0477383165079343e-05,
"loss": 3.5427,
"step": 1192448
},
{
"epoch": 1.02,
"learning_rate": 3.0468997217568823e-05,
"loss": 3.5377,
"step": 1192960
},
{
"epoch": 1.02,
"learning_rate": 3.0460611270058303e-05,
"loss": 3.5508,
"step": 1193472
},
{
"epoch": 1.02,
"learning_rate": 3.0452225322547783e-05,
"loss": 3.5285,
"step": 1193984
},
{
"epoch": 1.02,
"learning_rate": 3.0443855753840995e-05,
"loss": 3.5297,
"step": 1194496
},
{
"epoch": 1.02,
"learning_rate": 3.0435469806330475e-05,
"loss": 3.5341,
"step": 1195008
},
{
"epoch": 1.02,
"learning_rate": 3.0427083858819955e-05,
"loss": 3.5365,
"step": 1195520
},
{
"epoch": 1.02,
"learning_rate": 3.0418697911309435e-05,
"loss": 3.5367,
"step": 1196032
},
{
"epoch": 1.02,
"learning_rate": 3.0410328342602644e-05,
"loss": 3.5346,
"step": 1196544
},
{
"epoch": 1.02,
"learning_rate": 3.0401942395092124e-05,
"loss": 3.5343,
"step": 1197056
},
{
"epoch": 1.02,
"learning_rate": 3.0393556447581607e-05,
"loss": 3.5259,
"step": 1197568
},
{
"epoch": 1.02,
"learning_rate": 3.0385170500071087e-05,
"loss": 3.5451,
"step": 1198080
},
{
"epoch": 1.02,
"learning_rate": 3.0376784552560567e-05,
"loss": 3.519,
"step": 1198592
},
{
"epoch": 1.02,
"learning_rate": 3.0368398605050047e-05,
"loss": 3.5268,
"step": 1199104
},
{
"epoch": 1.02,
"learning_rate": 3.0360029036343256e-05,
"loss": 3.5354,
"step": 1199616
},
{
"epoch": 1.02,
"learning_rate": 3.0351643088832736e-05,
"loss": 3.5333,
"step": 1200128
},
{
"epoch": 1.02,
"learning_rate": 3.0343257141322216e-05,
"loss": 3.5229,
"step": 1200640
},
{
"epoch": 1.02,
"learning_rate": 3.03348711938117e-05,
"loss": 3.5341,
"step": 1201152
},
{
"epoch": 1.02,
"learning_rate": 3.032650162510491e-05,
"loss": 3.5194,
"step": 1201664
},
{
"epoch": 1.02,
"learning_rate": 3.031811567759439e-05,
"loss": 3.5358,
"step": 1202176
},
{
"epoch": 1.02,
"learning_rate": 3.030972973008387e-05,
"loss": 3.5312,
"step": 1202688
},
{
"epoch": 1.02,
"learning_rate": 3.030134378257335e-05,
"loss": 3.5372,
"step": 1203200
},
{
"epoch": 1.02,
"learning_rate": 3.029297421386656e-05,
"loss": 3.5398,
"step": 1203712
},
{
"epoch": 1.02,
"learning_rate": 3.028458826635604e-05,
"loss": 3.5421,
"step": 1204224
},
{
"epoch": 1.02,
"learning_rate": 3.027620231884552e-05,
"loss": 3.5275,
"step": 1204736
},
{
"epoch": 1.02,
"learning_rate": 3.0267816371335e-05,
"loss": 3.5334,
"step": 1205248
},
{
"epoch": 1.02,
"learning_rate": 3.025944680262821e-05,
"loss": 3.5327,
"step": 1205760
},
{
"epoch": 1.02,
"learning_rate": 3.025106085511769e-05,
"loss": 3.5295,
"step": 1206272
},
{
"epoch": 1.02,
"learning_rate": 3.024267490760717e-05,
"loss": 3.5322,
"step": 1206784
},
{
"epoch": 1.02,
"learning_rate": 3.0234288960096653e-05,
"loss": 3.5276,
"step": 1207296
},
{
"epoch": 1.02,
"learning_rate": 3.0225903012586133e-05,
"loss": 3.5308,
"step": 1207808
},
{
"epoch": 1.02,
"learning_rate": 3.0217517065075606e-05,
"loss": 3.527,
"step": 1208320
},
{
"epoch": 1.02,
"learning_rate": 3.0209147496368822e-05,
"loss": 3.5257,
"step": 1208832
},
{
"epoch": 1.02,
"learning_rate": 3.0200761548858302e-05,
"loss": 3.5286,
"step": 1209344
},
{
"epoch": 1.02,
"learning_rate": 3.0192375601347782e-05,
"loss": 3.5276,
"step": 1209856
},
{
"epoch": 1.02,
"learning_rate": 3.018398965383726e-05,
"loss": 3.5266,
"step": 1210368
},
{
"epoch": 1.02,
"learning_rate": 3.0175620085130475e-05,
"loss": 3.5321,
"step": 1210880
},
{
"epoch": 1.02,
"learning_rate": 3.0167234137619955e-05,
"loss": 3.536,
"step": 1211392
},
{
"epoch": 1.02,
"learning_rate": 3.0158848190109428e-05,
"loss": 3.5479,
"step": 1211904
},
{
"epoch": 1.02,
"learning_rate": 3.0150462242598908e-05,
"loss": 3.5254,
"step": 1212416
},
{
"epoch": 1.02,
"learning_rate": 3.0142092673892124e-05,
"loss": 3.53,
"step": 1212928
},
{
"epoch": 1.02,
"learning_rate": 3.0133706726381604e-05,
"loss": 3.5394,
"step": 1213440
},
{
"epoch": 1.02,
"learning_rate": 3.012532077887108e-05,
"loss": 3.5328,
"step": 1213952
},
{
"epoch": 1.02,
"learning_rate": 3.011693483136056e-05,
"loss": 3.5329,
"step": 1214464
},
{
"epoch": 1.02,
"learning_rate": 3.0108565262653776e-05,
"loss": 3.5326,
"step": 1214976
},
{
"epoch": 1.02,
"learning_rate": 3.0100179315143256e-05,
"loss": 3.5407,
"step": 1215488
},
{
"epoch": 1.02,
"learning_rate": 3.0091793367632733e-05,
"loss": 3.5325,
"step": 1216000
},
{
"epoch": 1.02,
"learning_rate": 3.0083407420122213e-05,
"loss": 3.5357,
"step": 1216512
},
{
"epoch": 1.02,
"learning_rate": 3.007503785141543e-05,
"loss": 3.5299,
"step": 1217024
},
{
"epoch": 1.02,
"learning_rate": 3.00666519039049e-05,
"loss": 3.5285,
"step": 1217536
},
{
"epoch": 1.02,
"learning_rate": 3.005826595639438e-05,
"loss": 3.5316,
"step": 1218048
},
{
"epoch": 1.02,
"learning_rate": 3.004988000888386e-05,
"loss": 3.5274,
"step": 1218560
},
{
"epoch": 1.02,
"learning_rate": 3.0041510440177077e-05,
"loss": 3.5358,
"step": 1219072
},
{
"epoch": 1.02,
"learning_rate": 3.0033124492666554e-05,
"loss": 3.528,
"step": 1219584
},
{
"epoch": 1.02,
"learning_rate": 3.0024738545156034e-05,
"loss": 3.5427,
"step": 1220096
},
{
"epoch": 1.02,
"learning_rate": 3.0016352597645514e-05,
"loss": 3.5203,
"step": 1220608
},
{
"epoch": 1.03,
"learning_rate": 3.0007966650134994e-05,
"loss": 3.5293,
"step": 1221120
},
{
"epoch": 1.03,
"eval_loss": 3.8462672233581543,
"eval_runtime": 305.3329,
"eval_samples_per_second": 1249.754,
"eval_steps_per_second": 39.056,
"step": 1221120
},
{
"epoch": 0.0,
"learning_rate": 2.9999580702624474e-05,
"loss": 3.5259,
"step": 1221632
},
{
"epoch": 0.0,
"learning_rate": 2.9991194755113954e-05,
"loss": 3.5227,
"step": 1222144
},
{
"epoch": 0.0,
"learning_rate": 2.9982808807603434e-05,
"loss": 3.5336,
"step": 1222656
},
{
"epoch": 0.0,
"learning_rate": 2.9974422860092917e-05,
"loss": 3.5398,
"step": 1223168
},
{
"epoch": 0.0,
"learning_rate": 2.9966053291386126e-05,
"loss": 3.5352,
"step": 1223680
},
{
"epoch": 0.0,
"learning_rate": 2.9957667343875606e-05,
"loss": 3.5242,
"step": 1224192
},
{
"epoch": 0.0,
"learning_rate": 2.9949281396365086e-05,
"loss": 3.5253,
"step": 1224704
},
{
"epoch": 0.0,
"learning_rate": 2.9940895448854566e-05,
"loss": 3.5182,
"step": 1225216
},
{
"epoch": 0.0,
"learning_rate": 2.993252588014778e-05,
"loss": 3.5378,
"step": 1225728
},
{
"epoch": 0.0,
"learning_rate": 2.992413993263726e-05,
"loss": 3.5243,
"step": 1226240
},
{
"epoch": 0.0,
"learning_rate": 2.991575398512674e-05,
"loss": 3.5387,
"step": 1226752
},
{
"epoch": 0.0,
"learning_rate": 2.990736803761622e-05,
"loss": 3.5288,
"step": 1227264
},
{
"epoch": 0.0,
"learning_rate": 2.9898998468909427e-05,
"loss": 3.5198,
"step": 1227776
},
{
"epoch": 0.0,
"learning_rate": 2.9890612521398907e-05,
"loss": 3.5209,
"step": 1228288
},
{
"epoch": 0.0,
"learning_rate": 2.9882226573888387e-05,
"loss": 3.5182,
"step": 1228800
},
{
"epoch": 0.0,
"learning_rate": 2.987384062637787e-05,
"loss": 3.5273,
"step": 1229312
},
{
"epoch": 0.0,
"learning_rate": 2.986547105767108e-05,
"loss": 3.5245,
"step": 1229824
},
{
"epoch": 0.0,
"learning_rate": 2.985708511016056e-05,
"loss": 3.5239,
"step": 1230336
},
{
"epoch": 0.0,
"learning_rate": 2.984869916265004e-05,
"loss": 3.5227,
"step": 1230848
},
{
"epoch": 0.0,
"learning_rate": 2.984031321513952e-05,
"loss": 3.5372,
"step": 1231360
},
{
"epoch": 0.0,
"learning_rate": 2.9831943646432732e-05,
"loss": 3.5306,
"step": 1231872
},
{
"epoch": 0.0,
"learning_rate": 2.9823557698922212e-05,
"loss": 3.5318,
"step": 1232384
},
{
"epoch": 0.0,
"learning_rate": 2.9815171751411692e-05,
"loss": 3.5241,
"step": 1232896
},
{
"epoch": 0.0,
"learning_rate": 2.9806785803901172e-05,
"loss": 3.535,
"step": 1233408
},
{
"epoch": 0.0,
"learning_rate": 2.979841623519438e-05,
"loss": 3.5256,
"step": 1233920
},
{
"epoch": 0.0,
"learning_rate": 2.979003028768386e-05,
"loss": 3.5253,
"step": 1234432
},
{
"epoch": 0.0,
"learning_rate": 2.978164434017334e-05,
"loss": 3.5284,
"step": 1234944
},
{
"epoch": 0.0,
"learning_rate": 2.9773258392662824e-05,
"loss": 3.5163,
"step": 1235456
},
{
"epoch": 0.0,
"learning_rate": 2.9764888823956033e-05,
"loss": 3.5194,
"step": 1235968
},
{
"epoch": 0.01,
"learning_rate": 2.9756502876445513e-05,
"loss": 3.5159,
"step": 1236480
},
{
"epoch": 0.01,
"learning_rate": 2.9748116928934993e-05,
"loss": 3.5276,
"step": 1236992
},
{
"epoch": 0.01,
"learning_rate": 2.9739730981424473e-05,
"loss": 3.5286,
"step": 1237504
},
{
"epoch": 0.01,
"learning_rate": 2.9731345033913953e-05,
"loss": 3.5311,
"step": 1238016
},
{
"epoch": 0.01,
"learning_rate": 2.9722975465207166e-05,
"loss": 3.528,
"step": 1238528
},
{
"epoch": 0.01,
"learning_rate": 2.9714589517696646e-05,
"loss": 3.5277,
"step": 1239040
},
{
"epoch": 0.01,
"learning_rate": 2.9706203570186126e-05,
"loss": 3.5332,
"step": 1239552
},
{
"epoch": 0.01,
"learning_rate": 2.9697817622675606e-05,
"loss": 3.5179,
"step": 1240064
},
{
"epoch": 0.01,
"learning_rate": 2.9689448053968815e-05,
"loss": 3.5254,
"step": 1240576
},
{
"epoch": 0.01,
"learning_rate": 2.9681062106458295e-05,
"loss": 3.5107,
"step": 1241088
},
{
"epoch": 0.01,
"learning_rate": 2.9672676158947778e-05,
"loss": 3.5242,
"step": 1241600
},
{
"epoch": 0.01,
"learning_rate": 2.9664290211437258e-05,
"loss": 3.5162,
"step": 1242112
},
{
"epoch": 0.01,
"learning_rate": 2.9655904263926738e-05,
"loss": 3.5339,
"step": 1242624
},
{
"epoch": 0.01,
"learning_rate": 2.9647534695219947e-05,
"loss": 3.5242,
"step": 1243136
},
{
"epoch": 0.01,
"learning_rate": 2.9639148747709427e-05,
"loss": 3.5207,
"step": 1243648
},
{
"epoch": 0.01,
"learning_rate": 2.9630762800198907e-05,
"loss": 3.5289,
"step": 1244160
},
{
"epoch": 0.01,
"learning_rate": 2.9622376852688387e-05,
"loss": 3.5204,
"step": 1244672
},
{
"epoch": 0.01,
"learning_rate": 2.96140072839816e-05,
"loss": 3.5194,
"step": 1245184
},
{
"epoch": 0.01,
"learning_rate": 2.960562133647108e-05,
"loss": 3.5006,
"step": 1245696
},
{
"epoch": 0.01,
"learning_rate": 2.959723538896056e-05,
"loss": 3.5248,
"step": 1246208
},
{
"epoch": 0.01,
"learning_rate": 2.9588849441450032e-05,
"loss": 3.5272,
"step": 1246720
},
{
"epoch": 0.01,
"learning_rate": 2.9580463493939516e-05,
"loss": 3.5269,
"step": 1247232
},
{
"epoch": 0.01,
"learning_rate": 2.957209392523273e-05,
"loss": 3.5152,
"step": 1247744
},
{
"epoch": 0.01,
"learning_rate": 2.956370797772221e-05,
"loss": 3.5128,
"step": 1248256
},
{
"epoch": 0.01,
"learning_rate": 2.9555322030211685e-05,
"loss": 3.5136,
"step": 1248768
},
{
"epoch": 0.01,
"learning_rate": 2.9546936082701165e-05,
"loss": 3.5113,
"step": 1249280
},
{
"epoch": 0.01,
"learning_rate": 2.953856651399438e-05,
"loss": 3.5327,
"step": 1249792
},
{
"epoch": 0.01,
"learning_rate": 2.953018056648386e-05,
"loss": 3.5102,
"step": 1250304
},
{
"epoch": 0.01,
"learning_rate": 2.9521794618973337e-05,
"loss": 3.5284,
"step": 1250816
},
{
"epoch": 0.01,
"learning_rate": 2.9513408671462817e-05,
"loss": 3.5238,
"step": 1251328
},
{
"epoch": 0.01,
"learning_rate": 2.9505039102756033e-05,
"loss": 3.507,
"step": 1251840
},
{
"epoch": 0.01,
"learning_rate": 2.9496653155245506e-05,
"loss": 3.5222,
"step": 1252352
},
{
"epoch": 0.01,
"learning_rate": 2.9488267207734986e-05,
"loss": 3.5164,
"step": 1252864
},
{
"epoch": 0.01,
"learning_rate": 2.947988126022447e-05,
"loss": 3.5162,
"step": 1253376
},
{
"epoch": 0.01,
"learning_rate": 2.9471511691517685e-05,
"loss": 3.511,
"step": 1253888
},
{
"epoch": 0.01,
"learning_rate": 2.946312574400716e-05,
"loss": 3.5275,
"step": 1254400
},
{
"epoch": 0.01,
"learning_rate": 2.945473979649664e-05,
"loss": 3.5158,
"step": 1254912
},
{
"epoch": 0.01,
"learning_rate": 2.944635384898612e-05,
"loss": 3.5129,
"step": 1255424
},
{
"epoch": 0.01,
"learning_rate": 2.943798428027933e-05,
"loss": 3.5113,
"step": 1255936
},
{
"epoch": 0.01,
"learning_rate": 2.942959833276881e-05,
"loss": 3.5135,
"step": 1256448
},
{
"epoch": 0.01,
"learning_rate": 2.942121238525829e-05,
"loss": 3.5179,
"step": 1256960
},
{
"epoch": 0.01,
"learning_rate": 2.941282643774777e-05,
"loss": 3.5301,
"step": 1257472
},
{
"epoch": 0.01,
"learning_rate": 2.940444049023725e-05,
"loss": 3.5166,
"step": 1257984
},
{
"epoch": 0.01,
"learning_rate": 2.939607092153046e-05,
"loss": 3.5269,
"step": 1258496
},
{
"epoch": 0.01,
"learning_rate": 2.938768497401994e-05,
"loss": 3.5303,
"step": 1259008
},
{
"epoch": 0.01,
"learning_rate": 2.9379299026509423e-05,
"loss": 3.5233,
"step": 1259520
},
{
"epoch": 0.01,
"learning_rate": 2.9370913078998903e-05,
"loss": 3.5201,
"step": 1260032
},
{
"epoch": 0.01,
"learning_rate": 2.9362543510292112e-05,
"loss": 3.5237,
"step": 1260544
},
{
"epoch": 0.01,
"learning_rate": 2.9354157562781592e-05,
"loss": 3.5262,
"step": 1261056
},
{
"epoch": 0.01,
"learning_rate": 2.9345771615271072e-05,
"loss": 3.5185,
"step": 1261568
},
{
"epoch": 0.01,
"learning_rate": 2.9337385667760552e-05,
"loss": 3.5192,
"step": 1262080
},
{
"epoch": 0.01,
"learning_rate": 2.9329016099053765e-05,
"loss": 3.5314,
"step": 1262592
},
{
"epoch": 0.01,
"learning_rate": 2.9320630151543244e-05,
"loss": 3.5326,
"step": 1263104
},
{
"epoch": 0.01,
"learning_rate": 2.9312244204032724e-05,
"loss": 3.5167,
"step": 1263616
},
{
"epoch": 0.01,
"learning_rate": 2.9303858256522204e-05,
"loss": 3.5029,
"step": 1264128
},
{
"epoch": 0.01,
"learning_rate": 2.9295488687815413e-05,
"loss": 3.5146,
"step": 1264640
},
{
"epoch": 0.01,
"learning_rate": 2.9287102740304893e-05,
"loss": 3.5285,
"step": 1265152
},
{
"epoch": 0.01,
"learning_rate": 2.9278716792794373e-05,
"loss": 3.5218,
"step": 1265664
},
{
"epoch": 0.01,
"learning_rate": 2.9270330845283857e-05,
"loss": 3.5286,
"step": 1266176
},
{
"epoch": 0.01,
"learning_rate": 2.9261961276577066e-05,
"loss": 3.5153,
"step": 1266688
},
{
"epoch": 0.02,
"learning_rate": 2.9253575329066546e-05,
"loss": 3.5177,
"step": 1267200
},
{
"epoch": 0.02,
"learning_rate": 2.9245189381556026e-05,
"loss": 3.5106,
"step": 1267712
},
{
"epoch": 0.02,
"learning_rate": 2.9236803434045506e-05,
"loss": 3.5136,
"step": 1268224
},
{
"epoch": 0.02,
"learning_rate": 2.9228417486534986e-05,
"loss": 3.5269,
"step": 1268736
},
{
"epoch": 0.02,
"learning_rate": 2.9220047917828198e-05,
"loss": 3.5216,
"step": 1269248
},
{
"epoch": 0.02,
"learning_rate": 2.9211661970317678e-05,
"loss": 3.5375,
"step": 1269760
},
{
"epoch": 0.02,
"learning_rate": 2.9203276022807158e-05,
"loss": 3.5227,
"step": 1270272
},
{
"epoch": 0.02,
"learning_rate": 2.9194890075296638e-05,
"loss": 3.5109,
"step": 1270784
},
{
"epoch": 0.02,
"learning_rate": 2.9186520506589847e-05,
"loss": 3.5205,
"step": 1271296
},
{
"epoch": 0.02,
"learning_rate": 2.9178134559079327e-05,
"loss": 3.5233,
"step": 1271808
},
{
"epoch": 0.02,
"learning_rate": 2.916974861156881e-05,
"loss": 3.5225,
"step": 1272320
},
{
"epoch": 0.02,
"learning_rate": 2.916136266405829e-05,
"loss": 3.523,
"step": 1272832
},
{
"epoch": 0.02,
"learning_rate": 2.91529930953515e-05,
"loss": 3.517,
"step": 1273344
},
{
"epoch": 0.02,
"learning_rate": 2.914460714784098e-05,
"loss": 3.5163,
"step": 1273856
},
{
"epoch": 0.02,
"learning_rate": 2.913622120033046e-05,
"loss": 3.5255,
"step": 1274368
},
{
"epoch": 0.02,
"learning_rate": 2.912783525281994e-05,
"loss": 3.5062,
"step": 1274880
},
{
"epoch": 0.02,
"learning_rate": 2.9119465684113152e-05,
"loss": 3.5153,
"step": 1275392
},
{
"epoch": 0.02,
"learning_rate": 2.9111079736602632e-05,
"loss": 3.5204,
"step": 1275904
},
{
"epoch": 0.02,
"learning_rate": 2.9102693789092112e-05,
"loss": 3.518,
"step": 1276416
},
{
"epoch": 0.02,
"learning_rate": 2.909430784158159e-05,
"loss": 3.5098,
"step": 1276928
},
{
"epoch": 0.02,
"learning_rate": 2.90859382728748e-05,
"loss": 3.5246,
"step": 1277440
},
{
"epoch": 0.02,
"learning_rate": 2.907755232536428e-05,
"loss": 3.5069,
"step": 1277952
},
{
"epoch": 0.02,
"learning_rate": 2.9069166377853764e-05,
"loss": 3.5184,
"step": 1278464
},
{
"epoch": 0.02,
"learning_rate": 2.9060780430343244e-05,
"loss": 3.5174,
"step": 1278976
},
{
"epoch": 0.02,
"learning_rate": 2.9052394482832724e-05,
"loss": 3.5239,
"step": 1279488
},
{
"epoch": 0.02,
"learning_rate": 2.9044024914125933e-05,
"loss": 3.5274,
"step": 1280000
},
{
"epoch": 0.02,
"learning_rate": 2.9035638966615413e-05,
"loss": 3.5248,
"step": 1280512
},
{
"epoch": 0.02,
"learning_rate": 2.9027253019104893e-05,
"loss": 3.5135,
"step": 1281024
},
{
"epoch": 0.02,
"learning_rate": 2.9018867071594373e-05,
"loss": 3.5179,
"step": 1281536
},
{
"epoch": 0.02,
"learning_rate": 2.9010497502887585e-05,
"loss": 3.5232,
"step": 1282048
},
{
"epoch": 0.02,
"learning_rate": 2.9002111555377065e-05,
"loss": 3.5152,
"step": 1282560
},
{
"epoch": 0.02,
"learning_rate": 2.8993725607866545e-05,
"loss": 3.5179,
"step": 1283072
},
{
"epoch": 0.02,
"learning_rate": 2.8985339660356025e-05,
"loss": 3.5152,
"step": 1283584
},
{
"epoch": 0.02,
"learning_rate": 2.8976970091649234e-05,
"loss": 3.5152,
"step": 1284096
},
{
"epoch": 0.02,
"learning_rate": 2.8968584144138718e-05,
"loss": 3.5188,
"step": 1284608
},
{
"epoch": 0.02,
"learning_rate": 2.8960198196628198e-05,
"loss": 3.5116,
"step": 1285120
},
{
"epoch": 0.02,
"learning_rate": 2.8951812249117678e-05,
"loss": 3.515,
"step": 1285632
},
{
"epoch": 0.02,
"learning_rate": 2.8943442680410887e-05,
"loss": 3.514,
"step": 1286144
},
{
"epoch": 0.02,
"learning_rate": 2.8935056732900367e-05,
"loss": 3.5128,
"step": 1286656
},
{
"epoch": 0.02,
"learning_rate": 2.8926670785389847e-05,
"loss": 3.5134,
"step": 1287168
},
{
"epoch": 0.02,
"learning_rate": 2.8918284837879327e-05,
"loss": 3.5243,
"step": 1287680
},
{
"epoch": 0.02,
"learning_rate": 2.890989889036881e-05,
"loss": 3.5327,
"step": 1288192
},
{
"epoch": 0.02,
"learning_rate": 2.890152932166202e-05,
"loss": 3.5202,
"step": 1288704
},
{
"epoch": 0.02,
"learning_rate": 2.88931433741515e-05,
"loss": 3.5078,
"step": 1289216
},
{
"epoch": 0.02,
"learning_rate": 2.888475742664098e-05,
"loss": 3.5202,
"step": 1289728
},
{
"epoch": 0.02,
"learning_rate": 2.887637147913046e-05,
"loss": 3.5221,
"step": 1290240
},
{
"epoch": 0.02,
"learning_rate": 2.886800191042367e-05,
"loss": 3.5222,
"step": 1290752
},
{
"epoch": 0.02,
"learning_rate": 2.885961596291315e-05,
"loss": 3.5215,
"step": 1291264
},
{
"epoch": 0.02,
"learning_rate": 2.885123001540263e-05,
"loss": 3.5267,
"step": 1291776
},
{
"epoch": 0.02,
"learning_rate": 2.884284406789211e-05,
"loss": 3.5179,
"step": 1292288
},
{
"epoch": 0.02,
"learning_rate": 2.883447449918532e-05,
"loss": 3.5224,
"step": 1292800
},
{
"epoch": 0.02,
"learning_rate": 2.88260885516748e-05,
"loss": 3.5153,
"step": 1293312
},
{
"epoch": 0.02,
"learning_rate": 2.881770260416428e-05,
"loss": 3.5185,
"step": 1293824
},
{
"epoch": 0.02,
"learning_rate": 2.8809316656653764e-05,
"loss": 3.5169,
"step": 1294336
},
{
"epoch": 0.02,
"learning_rate": 2.8800947087946973e-05,
"loss": 3.5112,
"step": 1294848
},
{
"epoch": 0.02,
"learning_rate": 2.8792561140436453e-05,
"loss": 3.5255,
"step": 1295360
},
{
"epoch": 0.02,
"learning_rate": 2.8784175192925933e-05,
"loss": 3.5133,
"step": 1295872
},
{
"epoch": 0.02,
"learning_rate": 2.877578924541541e-05,
"loss": 3.529,
"step": 1296384
},
{
"epoch": 0.02,
"learning_rate": 2.8767419676708625e-05,
"loss": 3.5103,
"step": 1296896
},
{
"epoch": 0.02,
"learning_rate": 2.8759033729198105e-05,
"loss": 3.5111,
"step": 1297408
},
{
"epoch": 0.03,
"eval_loss": 3.846646785736084,
"eval_runtime": 304.6588,
"eval_samples_per_second": 1252.519,
"eval_steps_per_second": 39.142,
"step": 1297440
},
{
"epoch": 1.0,
"learning_rate": 2.8750647781687585e-05,
"loss": 3.5119,
"step": 1297920
},
{
"epoch": 1.0,
"learning_rate": 2.8742261834177058e-05,
"loss": 3.5105,
"step": 1298432
},
{
"epoch": 1.0,
"learning_rate": 2.8733892265470274e-05,
"loss": 3.5232,
"step": 1298944
},
{
"epoch": 1.0,
"learning_rate": 2.8725506317959754e-05,
"loss": 3.519,
"step": 1299456
},
{
"epoch": 1.0,
"learning_rate": 2.8717120370449234e-05,
"loss": 3.5229,
"step": 1299968
},
{
"epoch": 1.0,
"learning_rate": 2.870873442293871e-05,
"loss": 3.5112,
"step": 1300480
},
{
"epoch": 1.0,
"learning_rate": 2.870034847542819e-05,
"loss": 3.5081,
"step": 1300992
},
{
"epoch": 1.0,
"learning_rate": 2.8691978906721406e-05,
"loss": 3.5081,
"step": 1301504
},
{
"epoch": 1.0,
"learning_rate": 2.868359295921088e-05,
"loss": 3.5229,
"step": 1302016
},
{
"epoch": 1.0,
"learning_rate": 2.8675207011700363e-05,
"loss": 3.5141,
"step": 1302528
},
{
"epoch": 1.0,
"learning_rate": 2.8666821064189843e-05,
"loss": 3.5248,
"step": 1303040
},
{
"epoch": 1.0,
"learning_rate": 2.865845149548306e-05,
"loss": 3.5133,
"step": 1303552
},
{
"epoch": 1.0,
"learning_rate": 2.8650065547972532e-05,
"loss": 3.5103,
"step": 1304064
},
{
"epoch": 1.0,
"learning_rate": 2.8641679600462012e-05,
"loss": 3.5067,
"step": 1304576
},
{
"epoch": 1.0,
"learning_rate": 2.8633293652951492e-05,
"loss": 3.5054,
"step": 1305088
},
{
"epoch": 1.0,
"learning_rate": 2.8624907705440972e-05,
"loss": 3.5053,
"step": 1305600
},
{
"epoch": 1.0,
"learning_rate": 2.8616538136734184e-05,
"loss": 3.5136,
"step": 1306112
},
{
"epoch": 1.0,
"learning_rate": 2.8608152189223664e-05,
"loss": 3.5101,
"step": 1306624
},
{
"epoch": 1.0,
"learning_rate": 2.8599766241713144e-05,
"loss": 3.506,
"step": 1307136
},
{
"epoch": 1.0,
"learning_rate": 2.8591380294202624e-05,
"loss": 3.5291,
"step": 1307648
},
{
"epoch": 1.0,
"learning_rate": 2.8583010725495833e-05,
"loss": 3.5162,
"step": 1308160
},
{
"epoch": 1.0,
"learning_rate": 2.8574624777985317e-05,
"loss": 3.5206,
"step": 1308672
},
{
"epoch": 1.0,
"learning_rate": 2.8566238830474796e-05,
"loss": 3.5094,
"step": 1309184
},
{
"epoch": 1.0,
"learning_rate": 2.8557852882964276e-05,
"loss": 3.5197,
"step": 1309696
},
{
"epoch": 1.0,
"learning_rate": 2.8549483314257486e-05,
"loss": 3.5069,
"step": 1310208
},
{
"epoch": 1.0,
"learning_rate": 2.8541097366746966e-05,
"loss": 3.5131,
"step": 1310720
},
{
"epoch": 1.0,
"learning_rate": 2.8532711419236445e-05,
"loss": 3.5124,
"step": 1311232
},
{
"epoch": 1.0,
"learning_rate": 2.8524325471725925e-05,
"loss": 3.5088,
"step": 1311744
},
{
"epoch": 1.0,
"learning_rate": 2.8515955903019138e-05,
"loss": 3.5012,
"step": 1312256
},
{
"epoch": 1.01,
"learning_rate": 2.8507569955508618e-05,
"loss": 3.5033,
"step": 1312768
},
{
"epoch": 1.01,
"learning_rate": 2.8499184007998098e-05,
"loss": 3.5125,
"step": 1313280
},
{
"epoch": 1.01,
"learning_rate": 2.8490798060487578e-05,
"loss": 3.5162,
"step": 1313792
},
{
"epoch": 1.01,
"learning_rate": 2.8482428491780787e-05,
"loss": 3.514,
"step": 1314304
},
{
"epoch": 1.01,
"learning_rate": 2.847404254427027e-05,
"loss": 3.518,
"step": 1314816
},
{
"epoch": 1.01,
"learning_rate": 2.846565659675975e-05,
"loss": 3.5135,
"step": 1315328
},
{
"epoch": 1.01,
"learning_rate": 2.845727064924923e-05,
"loss": 3.5156,
"step": 1315840
},
{
"epoch": 1.01,
"learning_rate": 2.844890108054244e-05,
"loss": 3.5056,
"step": 1316352
},
{
"epoch": 1.01,
"learning_rate": 2.844051513303192e-05,
"loss": 3.5117,
"step": 1316864
},
{
"epoch": 1.01,
"learning_rate": 2.84321291855214e-05,
"loss": 3.4989,
"step": 1317376
},
{
"epoch": 1.01,
"learning_rate": 2.842374323801088e-05,
"loss": 3.5125,
"step": 1317888
},
{
"epoch": 1.01,
"learning_rate": 2.841537366930409e-05,
"loss": 3.5018,
"step": 1318400
},
{
"epoch": 1.01,
"learning_rate": 2.840698772179357e-05,
"loss": 3.5196,
"step": 1318912
},
{
"epoch": 1.01,
"learning_rate": 2.839860177428305e-05,
"loss": 3.5073,
"step": 1319424
},
{
"epoch": 1.01,
"learning_rate": 2.839021582677253e-05,
"loss": 3.5082,
"step": 1319936
},
{
"epoch": 1.01,
"learning_rate": 2.838182987926201e-05,
"loss": 3.5142,
"step": 1320448
},
{
"epoch": 1.01,
"learning_rate": 2.837346031055522e-05,
"loss": 3.5081,
"step": 1320960
},
{
"epoch": 1.01,
"learning_rate": 2.8365074363044704e-05,
"loss": 3.5061,
"step": 1321472
},
{
"epoch": 1.01,
"learning_rate": 2.8356688415534184e-05,
"loss": 3.4937,
"step": 1321984
},
{
"epoch": 1.01,
"learning_rate": 2.8348302468023664e-05,
"loss": 3.5056,
"step": 1322496
},
{
"epoch": 1.01,
"learning_rate": 2.8339932899316873e-05,
"loss": 3.5134,
"step": 1323008
},
{
"epoch": 1.01,
"learning_rate": 2.8331546951806353e-05,
"loss": 3.5124,
"step": 1323520
},
{
"epoch": 1.01,
"learning_rate": 2.8323161004295833e-05,
"loss": 3.5035,
"step": 1324032
},
{
"epoch": 1.01,
"learning_rate": 2.8314775056785313e-05,
"loss": 3.4979,
"step": 1324544
},
{
"epoch": 1.01,
"learning_rate": 2.8306389109274796e-05,
"loss": 3.5045,
"step": 1325056
},
{
"epoch": 1.01,
"learning_rate": 2.8298019540568005e-05,
"loss": 3.4946,
"step": 1325568
},
{
"epoch": 1.01,
"learning_rate": 2.8289633593057485e-05,
"loss": 3.5205,
"step": 1326080
},
{
"epoch": 1.01,
"learning_rate": 2.8281247645546965e-05,
"loss": 3.4979,
"step": 1326592
},
{
"epoch": 1.01,
"learning_rate": 2.8272861698036445e-05,
"loss": 3.5152,
"step": 1327104
},
{
"epoch": 1.01,
"learning_rate": 2.8264492129329657e-05,
"loss": 3.5081,
"step": 1327616
},
{
"epoch": 1.01,
"learning_rate": 2.8256106181819137e-05,
"loss": 3.495,
"step": 1328128
},
{
"epoch": 1.01,
"learning_rate": 2.8247720234308617e-05,
"loss": 3.5085,
"step": 1328640
},
{
"epoch": 1.01,
"learning_rate": 2.8239350665601827e-05,
"loss": 3.5064,
"step": 1329152
},
{
"epoch": 1.01,
"learning_rate": 2.8230964718091306e-05,
"loss": 3.4989,
"step": 1329664
},
{
"epoch": 1.01,
"learning_rate": 2.8222578770580786e-05,
"loss": 3.4985,
"step": 1330176
},
{
"epoch": 1.01,
"learning_rate": 2.8214192823070266e-05,
"loss": 3.5125,
"step": 1330688
},
{
"epoch": 1.01,
"learning_rate": 2.820580687555975e-05,
"loss": 3.504,
"step": 1331200
},
{
"epoch": 1.01,
"learning_rate": 2.819743730685296e-05,
"loss": 3.4992,
"step": 1331712
},
{
"epoch": 1.01,
"learning_rate": 2.818905135934244e-05,
"loss": 3.4958,
"step": 1332224
},
{
"epoch": 1.01,
"learning_rate": 2.818066541183192e-05,
"loss": 3.5014,
"step": 1332736
},
{
"epoch": 1.01,
"learning_rate": 2.81722794643214e-05,
"loss": 3.5051,
"step": 1333248
},
{
"epoch": 1.01,
"learning_rate": 2.816390989561461e-05,
"loss": 3.5167,
"step": 1333760
},
{
"epoch": 1.01,
"learning_rate": 2.815552394810409e-05,
"loss": 3.503,
"step": 1334272
},
{
"epoch": 1.01,
"learning_rate": 2.814713800059357e-05,
"loss": 3.5171,
"step": 1334784
},
{
"epoch": 1.01,
"learning_rate": 2.813875205308305e-05,
"loss": 3.5136,
"step": 1335296
},
{
"epoch": 1.01,
"learning_rate": 2.813038248437626e-05,
"loss": 3.5107,
"step": 1335808
},
{
"epoch": 1.01,
"learning_rate": 2.812199653686574e-05,
"loss": 3.504,
"step": 1336320
},
{
"epoch": 1.01,
"learning_rate": 2.811361058935522e-05,
"loss": 3.5134,
"step": 1336832
},
{
"epoch": 1.01,
"learning_rate": 2.8105224641844703e-05,
"loss": 3.514,
"step": 1337344
},
{
"epoch": 1.01,
"learning_rate": 2.8096855073137912e-05,
"loss": 3.503,
"step": 1337856
},
{
"epoch": 1.01,
"learning_rate": 2.8088469125627392e-05,
"loss": 3.5061,
"step": 1338368
},
{
"epoch": 1.01,
"learning_rate": 2.8080083178116872e-05,
"loss": 3.5129,
"step": 1338880
},
{
"epoch": 1.01,
"learning_rate": 2.8071697230606352e-05,
"loss": 3.5187,
"step": 1339392
},
{
"epoch": 1.01,
"learning_rate": 2.8063327661899565e-05,
"loss": 3.5049,
"step": 1339904
},
{
"epoch": 1.01,
"learning_rate": 2.8054941714389045e-05,
"loss": 3.4952,
"step": 1340416
},
{
"epoch": 1.01,
"learning_rate": 2.8046555766878525e-05,
"loss": 3.4989,
"step": 1340928
},
{
"epoch": 1.01,
"learning_rate": 2.8038169819368005e-05,
"loss": 3.5115,
"step": 1341440
},
{
"epoch": 1.01,
"learning_rate": 2.8029783871857485e-05,
"loss": 3.5097,
"step": 1341952
},
{
"epoch": 1.01,
"learning_rate": 2.8021414303150694e-05,
"loss": 3.5139,
"step": 1342464
},
{
"epoch": 1.01,
"learning_rate": 2.8013028355640174e-05,
"loss": 3.5049,
"step": 1342976
},
{
"epoch": 1.02,
"learning_rate": 2.8004642408129657e-05,
"loss": 3.501,
"step": 1343488
},
{
"epoch": 1.02,
"learning_rate": 2.7996256460619137e-05,
"loss": 3.4976,
"step": 1344000
},
{
"epoch": 1.02,
"learning_rate": 2.798787051310861e-05,
"loss": 3.5035,
"step": 1344512
},
{
"epoch": 1.02,
"learning_rate": 2.7979500944401826e-05,
"loss": 3.51,
"step": 1345024
},
{
"epoch": 1.02,
"learning_rate": 2.7971114996891306e-05,
"loss": 3.5075,
"step": 1345536
},
{
"epoch": 1.02,
"learning_rate": 2.7962729049380786e-05,
"loss": 3.524,
"step": 1346048
},
{
"epoch": 1.02,
"learning_rate": 2.7954343101870263e-05,
"loss": 3.5113,
"step": 1346560
},
{
"epoch": 1.02,
"learning_rate": 2.794597353316348e-05,
"loss": 3.4958,
"step": 1347072
},
{
"epoch": 1.02,
"learning_rate": 2.793758758565296e-05,
"loss": 3.5099,
"step": 1347584
},
{
"epoch": 1.02,
"learning_rate": 2.792920163814243e-05,
"loss": 3.5066,
"step": 1348096
},
{
"epoch": 1.02,
"learning_rate": 2.792081569063191e-05,
"loss": 3.5092,
"step": 1348608
},
{
"epoch": 1.02,
"learning_rate": 2.7912446121925127e-05,
"loss": 3.5076,
"step": 1349120
},
{
"epoch": 1.02,
"learning_rate": 2.790406017441461e-05,
"loss": 3.5026,
"step": 1349632
},
{
"epoch": 1.02,
"learning_rate": 2.7895674226904084e-05,
"loss": 3.5043,
"step": 1350144
},
{
"epoch": 1.02,
"learning_rate": 2.7887288279393564e-05,
"loss": 3.5148,
"step": 1350656
},
{
"epoch": 1.02,
"learning_rate": 2.787891871068678e-05,
"loss": 3.4923,
"step": 1351168
},
{
"epoch": 1.02,
"learning_rate": 2.787053276317626e-05,
"loss": 3.5028,
"step": 1351680
},
{
"epoch": 1.02,
"learning_rate": 2.7862146815665736e-05,
"loss": 3.5039,
"step": 1352192
},
{
"epoch": 1.02,
"learning_rate": 2.7853760868155216e-05,
"loss": 3.5077,
"step": 1352704
},
{
"epoch": 1.02,
"learning_rate": 2.7845374920644696e-05,
"loss": 3.4924,
"step": 1353216
},
{
"epoch": 1.02,
"learning_rate": 2.7837005351937905e-05,
"loss": 3.5096,
"step": 1353728
},
{
"epoch": 1.02,
"learning_rate": 2.7828619404427385e-05,
"loss": 3.4988,
"step": 1354240
},
{
"epoch": 1.02,
"learning_rate": 2.7820233456916865e-05,
"loss": 3.5021,
"step": 1354752
},
{
"epoch": 1.02,
"learning_rate": 2.781184750940635e-05,
"loss": 3.5049,
"step": 1355264
},
{
"epoch": 1.02,
"learning_rate": 2.7803477940699558e-05,
"loss": 3.505,
"step": 1355776
},
{
"epoch": 1.02,
"learning_rate": 2.7795091993189038e-05,
"loss": 3.5177,
"step": 1356288
},
{
"epoch": 1.02,
"learning_rate": 2.7786706045678518e-05,
"loss": 3.5125,
"step": 1356800
},
{
"epoch": 1.02,
"learning_rate": 2.7778320098167997e-05,
"loss": 3.5038,
"step": 1357312
},
{
"epoch": 1.02,
"learning_rate": 2.776995052946121e-05,
"loss": 3.5065,
"step": 1357824
},
{
"epoch": 1.02,
"learning_rate": 2.776156458195069e-05,
"loss": 3.5069,
"step": 1358336
},
{
"epoch": 1.02,
"learning_rate": 2.775317863444017e-05,
"loss": 3.5046,
"step": 1358848
},
{
"epoch": 1.02,
"learning_rate": 2.774479268692965e-05,
"loss": 3.5029,
"step": 1359360
},
{
"epoch": 1.02,
"learning_rate": 2.773642311822286e-05,
"loss": 3.5019,
"step": 1359872
},
{
"epoch": 1.02,
"learning_rate": 2.772803717071234e-05,
"loss": 3.501,
"step": 1360384
},
{
"epoch": 1.02,
"learning_rate": 2.771965122320182e-05,
"loss": 3.5051,
"step": 1360896
},
{
"epoch": 1.02,
"learning_rate": 2.7711265275691302e-05,
"loss": 3.4954,
"step": 1361408
},
{
"epoch": 1.02,
"learning_rate": 2.770289570698451e-05,
"loss": 3.5034,
"step": 1361920
},
{
"epoch": 1.02,
"learning_rate": 2.769450975947399e-05,
"loss": 3.4989,
"step": 1362432
},
{
"epoch": 1.02,
"learning_rate": 2.768612381196347e-05,
"loss": 3.5026,
"step": 1362944
},
{
"epoch": 1.02,
"learning_rate": 2.767773786445295e-05,
"loss": 3.4981,
"step": 1363456
},
{
"epoch": 1.02,
"learning_rate": 2.7669368295746164e-05,
"loss": 3.513,
"step": 1363968
},
{
"epoch": 1.02,
"learning_rate": 2.7660982348235644e-05,
"loss": 3.5189,
"step": 1364480
},
{
"epoch": 1.02,
"learning_rate": 2.7652596400725124e-05,
"loss": 3.5061,
"step": 1364992
},
{
"epoch": 1.02,
"learning_rate": 2.7644210453214603e-05,
"loss": 3.4977,
"step": 1365504
},
{
"epoch": 1.02,
"learning_rate": 2.7635824505704083e-05,
"loss": 3.5068,
"step": 1366016
},
{
"epoch": 1.02,
"learning_rate": 2.7627454936997293e-05,
"loss": 3.5089,
"step": 1366528
},
{
"epoch": 1.02,
"learning_rate": 2.7619068989486773e-05,
"loss": 3.5101,
"step": 1367040
},
{
"epoch": 1.02,
"learning_rate": 2.7610683041976252e-05,
"loss": 3.5071,
"step": 1367552
},
{
"epoch": 1.02,
"learning_rate": 2.7602297094465736e-05,
"loss": 3.5121,
"step": 1368064
},
{
"epoch": 1.02,
"learning_rate": 2.7593927525758945e-05,
"loss": 3.5018,
"step": 1368576
},
{
"epoch": 1.02,
"learning_rate": 2.7585541578248425e-05,
"loss": 3.512,
"step": 1369088
},
{
"epoch": 1.02,
"learning_rate": 2.7577155630737905e-05,
"loss": 3.5021,
"step": 1369600
},
{
"epoch": 1.02,
"learning_rate": 2.7568769683227385e-05,
"loss": 3.5083,
"step": 1370112
},
{
"epoch": 1.02,
"learning_rate": 2.7560400114520597e-05,
"loss": 3.5041,
"step": 1370624
},
{
"epoch": 1.02,
"learning_rate": 2.7552014167010077e-05,
"loss": 3.4949,
"step": 1371136
},
{
"epoch": 1.02,
"learning_rate": 2.7543628219499557e-05,
"loss": 3.5118,
"step": 1371648
},
{
"epoch": 1.02,
"learning_rate": 2.7535242271989037e-05,
"loss": 3.5037,
"step": 1372160
},
{
"epoch": 1.02,
"learning_rate": 2.7526872703282246e-05,
"loss": 3.5123,
"step": 1372672
},
{
"epoch": 1.02,
"learning_rate": 2.7518486755771726e-05,
"loss": 3.4956,
"step": 1373184
},
{
"epoch": 1.02,
"learning_rate": 2.7510100808261206e-05,
"loss": 3.499,
"step": 1373696
},
{
"epoch": 1.03,
"eval_loss": 3.8482086658477783,
"eval_runtime": 305.6969,
"eval_samples_per_second": 1248.266,
"eval_steps_per_second": 39.009,
"step": 1373760
},
{
"epoch": 0.0,
"learning_rate": 2.750171486075069e-05,
"loss": 3.4998,
"step": 1374208
},
{
"epoch": 0.0,
"learning_rate": 2.749332891324017e-05,
"loss": 3.4954,
"step": 1374720
},
{
"epoch": 0.0,
"learning_rate": 2.748494296572965e-05,
"loss": 3.5109,
"step": 1375232
},
{
"epoch": 0.0,
"learning_rate": 2.747655701821913e-05,
"loss": 3.5054,
"step": 1375744
},
{
"epoch": 0.0,
"learning_rate": 2.746818744951234e-05,
"loss": 3.5138,
"step": 1376256
},
{
"epoch": 0.0,
"learning_rate": 2.745980150200182e-05,
"loss": 3.4964,
"step": 1376768
},
{
"epoch": 0.0,
"learning_rate": 2.74514155544913e-05,
"loss": 3.4978,
"step": 1377280
},
{
"epoch": 0.0,
"learning_rate": 2.744304598578451e-05,
"loss": 3.4914,
"step": 1377792
},
{
"epoch": 0.0,
"learning_rate": 2.743466003827399e-05,
"loss": 3.5061,
"step": 1378304
},
{
"epoch": 0.0,
"learning_rate": 2.742627409076347e-05,
"loss": 3.506,
"step": 1378816
},
{
"epoch": 0.0,
"learning_rate": 2.741788814325295e-05,
"loss": 3.5045,
"step": 1379328
},
{
"epoch": 0.0,
"learning_rate": 2.740950219574243e-05,
"loss": 3.5026,
"step": 1379840
},
{
"epoch": 0.0,
"learning_rate": 2.7401132627035643e-05,
"loss": 3.4946,
"step": 1380352
},
{
"epoch": 0.0,
"learning_rate": 2.7392746679525123e-05,
"loss": 3.4939,
"step": 1380864
},
{
"epoch": 0.0,
"learning_rate": 2.7384360732014603e-05,
"loss": 3.4926,
"step": 1381376
},
{
"epoch": 0.0,
"learning_rate": 2.7375974784504083e-05,
"loss": 3.4952,
"step": 1381888
},
{
"epoch": 0.0,
"learning_rate": 2.7367605215797292e-05,
"loss": 3.4979,
"step": 1382400
},
{
"epoch": 0.0,
"learning_rate": 2.7359219268286772e-05,
"loss": 3.4958,
"step": 1382912
},
{
"epoch": 0.0,
"learning_rate": 2.7350833320776252e-05,
"loss": 3.4939,
"step": 1383424
},
{
"epoch": 0.0,
"learning_rate": 2.7342447373265735e-05,
"loss": 3.5171,
"step": 1383936
},
{
"epoch": 0.0,
"learning_rate": 2.7334077804558944e-05,
"loss": 3.5013,
"step": 1384448
},
{
"epoch": 0.0,
"learning_rate": 2.7325691857048424e-05,
"loss": 3.5068,
"step": 1384960
},
{
"epoch": 0.0,
"learning_rate": 2.7317305909537904e-05,
"loss": 3.4971,
"step": 1385472
},
{
"epoch": 0.0,
"learning_rate": 2.7308919962027384e-05,
"loss": 3.5092,
"step": 1385984
},
{
"epoch": 0.0,
"learning_rate": 2.7300550393320597e-05,
"loss": 3.4888,
"step": 1386496
},
{
"epoch": 0.0,
"learning_rate": 2.7292164445810077e-05,
"loss": 3.5031,
"step": 1387008
},
{
"epoch": 0.0,
"learning_rate": 2.7283778498299557e-05,
"loss": 3.4986,
"step": 1387520
},
{
"epoch": 0.0,
"learning_rate": 2.7275392550789037e-05,
"loss": 3.4983,
"step": 1388032
},
{
"epoch": 0.0,
"learning_rate": 2.7267022982082246e-05,
"loss": 3.487,
"step": 1388544
},
{
"epoch": 0.01,
"learning_rate": 2.7258637034571726e-05,
"loss": 3.4891,
"step": 1389056
},
{
"epoch": 0.01,
"learning_rate": 2.7250251087061206e-05,
"loss": 3.4995,
"step": 1389568
},
{
"epoch": 0.01,
"learning_rate": 2.724186513955069e-05,
"loss": 3.5017,
"step": 1390080
},
{
"epoch": 0.01,
"learning_rate": 2.7233495570843898e-05,
"loss": 3.5019,
"step": 1390592
},
{
"epoch": 0.01,
"learning_rate": 2.7225109623333378e-05,
"loss": 3.5014,
"step": 1391104
},
{
"epoch": 0.01,
"learning_rate": 2.7216723675822858e-05,
"loss": 3.4997,
"step": 1391616
},
{
"epoch": 0.01,
"learning_rate": 2.7208337728312338e-05,
"loss": 3.5033,
"step": 1392128
},
{
"epoch": 0.01,
"learning_rate": 2.719996815960555e-05,
"loss": 3.4939,
"step": 1392640
},
{
"epoch": 0.01,
"learning_rate": 2.719158221209503e-05,
"loss": 3.4977,
"step": 1393152
},
{
"epoch": 0.01,
"learning_rate": 2.718319626458451e-05,
"loss": 3.4856,
"step": 1393664
},
{
"epoch": 0.01,
"learning_rate": 2.7174810317073984e-05,
"loss": 3.5006,
"step": 1394176
},
{
"epoch": 0.01,
"learning_rate": 2.71664407483672e-05,
"loss": 3.4907,
"step": 1394688
},
{
"epoch": 0.01,
"learning_rate": 2.715805480085668e-05,
"loss": 3.5053,
"step": 1395200
},
{
"epoch": 0.01,
"learning_rate": 2.714966885334616e-05,
"loss": 3.4954,
"step": 1395712
},
{
"epoch": 0.01,
"learning_rate": 2.7141282905835636e-05,
"loss": 3.4919,
"step": 1396224
},
{
"epoch": 0.01,
"learning_rate": 2.7132896958325116e-05,
"loss": 3.5054,
"step": 1396736
},
{
"epoch": 0.01,
"learning_rate": 2.7124527389618332e-05,
"loss": 3.4933,
"step": 1397248
},
{
"epoch": 0.01,
"learning_rate": 2.7116141442107812e-05,
"loss": 3.4959,
"step": 1397760
},
{
"epoch": 0.01,
"learning_rate": 2.7107755494597288e-05,
"loss": 3.4783,
"step": 1398272
},
{
"epoch": 0.01,
"learning_rate": 2.7099369547086768e-05,
"loss": 3.4951,
"step": 1398784
},
{
"epoch": 0.01,
"learning_rate": 2.7090999978379984e-05,
"loss": 3.4985,
"step": 1399296
},
{
"epoch": 0.01,
"learning_rate": 2.7082614030869457e-05,
"loss": 3.4976,
"step": 1399808
},
{
"epoch": 0.01,
"learning_rate": 2.7074228083358937e-05,
"loss": 3.4925,
"step": 1400320
},
{
"epoch": 0.01,
"learning_rate": 2.7065842135848417e-05,
"loss": 3.4799,
"step": 1400832
},
{
"epoch": 0.01,
"learning_rate": 2.7057456188337897e-05,
"loss": 3.4935,
"step": 1401344
},
{
"epoch": 0.01,
"learning_rate": 2.704908661963111e-05,
"loss": 3.4828,
"step": 1401856
},
{
"epoch": 0.01,
"learning_rate": 2.704070067212059e-05,
"loss": 3.5046,
"step": 1402368
},
{
"epoch": 0.01,
"learning_rate": 2.703231472461007e-05,
"loss": 3.4848,
"step": 1402880
},
{
"epoch": 0.01,
"learning_rate": 2.702392877709955e-05,
"loss": 3.5002,
"step": 1403392
},
{
"epoch": 0.01,
"learning_rate": 2.701555920839276e-05,
"loss": 3.4995,
"step": 1403904
},
{
"epoch": 0.01,
"learning_rate": 2.7007173260882242e-05,
"loss": 3.48,
"step": 1404416
},
{
"epoch": 0.01,
"learning_rate": 2.6998787313371722e-05,
"loss": 3.4905,
"step": 1404928
},
{
"epoch": 0.01,
"learning_rate": 2.6990401365861202e-05,
"loss": 3.4976,
"step": 1405440
},
{
"epoch": 0.01,
"learning_rate": 2.698203179715441e-05,
"loss": 3.4858,
"step": 1405952
},
{
"epoch": 0.01,
"learning_rate": 2.697364584964389e-05,
"loss": 3.4866,
"step": 1406464
},
{
"epoch": 0.01,
"learning_rate": 2.696525990213337e-05,
"loss": 3.4966,
"step": 1406976
},
{
"epoch": 0.01,
"learning_rate": 2.695687395462285e-05,
"loss": 3.4962,
"step": 1407488
},
{
"epoch": 0.01,
"learning_rate": 2.6948504385916063e-05,
"loss": 3.4835,
"step": 1408000
},
{
"epoch": 0.01,
"learning_rate": 2.6940118438405543e-05,
"loss": 3.4875,
"step": 1408512
},
{
"epoch": 0.01,
"learning_rate": 2.6931732490895023e-05,
"loss": 3.4831,
"step": 1409024
},
{
"epoch": 0.01,
"learning_rate": 2.6923346543384503e-05,
"loss": 3.4908,
"step": 1409536
},
{
"epoch": 0.01,
"learning_rate": 2.6914976974677712e-05,
"loss": 3.5065,
"step": 1410048
},
{
"epoch": 0.01,
"learning_rate": 2.6906591027167196e-05,
"loss": 3.491,
"step": 1410560
},
{
"epoch": 0.01,
"learning_rate": 2.6898205079656676e-05,
"loss": 3.5044,
"step": 1411072
},
{
"epoch": 0.01,
"learning_rate": 2.6889819132146156e-05,
"loss": 3.5011,
"step": 1411584
},
{
"epoch": 0.01,
"learning_rate": 2.6881449563439365e-05,
"loss": 3.4995,
"step": 1412096
},
{
"epoch": 0.01,
"learning_rate": 2.6873063615928845e-05,
"loss": 3.4871,
"step": 1412608
},
{
"epoch": 0.01,
"learning_rate": 2.6864677668418325e-05,
"loss": 3.5037,
"step": 1413120
},
{
"epoch": 0.01,
"learning_rate": 2.6856291720907804e-05,
"loss": 3.498,
"step": 1413632
},
{
"epoch": 0.01,
"learning_rate": 2.6847922152201017e-05,
"loss": 3.4956,
"step": 1414144
},
{
"epoch": 0.01,
"learning_rate": 2.6839536204690497e-05,
"loss": 3.4929,
"step": 1414656
},
{
"epoch": 0.01,
"learning_rate": 2.6831150257179977e-05,
"loss": 3.4997,
"step": 1415168
},
{
"epoch": 0.01,
"learning_rate": 2.6822764309669457e-05,
"loss": 3.5098,
"step": 1415680
},
{
"epoch": 0.01,
"learning_rate": 2.6814394740962666e-05,
"loss": 3.4935,
"step": 1416192
},
{
"epoch": 0.01,
"learning_rate": 2.6806008793452146e-05,
"loss": 3.4806,
"step": 1416704
},
{
"epoch": 0.01,
"learning_rate": 2.679762284594163e-05,
"loss": 3.4844,
"step": 1417216
},
{
"epoch": 0.01,
"learning_rate": 2.678923689843111e-05,
"loss": 3.4978,
"step": 1417728
},
{
"epoch": 0.01,
"learning_rate": 2.6780867329724318e-05,
"loss": 3.4994,
"step": 1418240
},
{
"epoch": 0.01,
"learning_rate": 2.6772481382213798e-05,
"loss": 3.5028,
"step": 1418752
},
{
"epoch": 0.01,
"learning_rate": 2.6764095434703278e-05,
"loss": 3.4917,
"step": 1419264
},
{
"epoch": 0.02,
"learning_rate": 2.6755709487192758e-05,
"loss": 3.4918,
"step": 1419776
},
{
"epoch": 0.02,
"learning_rate": 2.674733991848597e-05,
"loss": 3.4822,
"step": 1420288
},
{
"epoch": 0.02,
"learning_rate": 2.673895397097545e-05,
"loss": 3.489,
"step": 1420800
},
{
"epoch": 0.02,
"learning_rate": 2.673056802346493e-05,
"loss": 3.4975,
"step": 1421312
},
{
"epoch": 0.02,
"learning_rate": 2.672218207595441e-05,
"loss": 3.4954,
"step": 1421824
},
{
"epoch": 0.02,
"learning_rate": 2.671381250724762e-05,
"loss": 3.5129,
"step": 1422336
},
{
"epoch": 0.02,
"learning_rate": 2.67054265597371e-05,
"loss": 3.4957,
"step": 1422848
},
{
"epoch": 0.02,
"learning_rate": 2.6697040612226583e-05,
"loss": 3.487,
"step": 1423360
},
{
"epoch": 0.02,
"learning_rate": 2.6688654664716063e-05,
"loss": 3.4974,
"step": 1423872
},
{
"epoch": 0.02,
"learning_rate": 2.6680285096009272e-05,
"loss": 3.4916,
"step": 1424384
},
{
"epoch": 0.02,
"learning_rate": 2.6671899148498752e-05,
"loss": 3.5004,
"step": 1424896
},
{
"epoch": 0.02,
"learning_rate": 2.6663513200988232e-05,
"loss": 3.4947,
"step": 1425408
},
{
"epoch": 0.02,
"learning_rate": 2.6655127253477712e-05,
"loss": 3.4887,
"step": 1425920
},
{
"epoch": 0.02,
"learning_rate": 2.6646741305967192e-05,
"loss": 3.4917,
"step": 1426432
},
{
"epoch": 0.02,
"learning_rate": 2.6638371737260404e-05,
"loss": 3.5015,
"step": 1426944
},
{
"epoch": 0.02,
"learning_rate": 2.6629985789749884e-05,
"loss": 3.4797,
"step": 1427456
},
{
"epoch": 0.02,
"learning_rate": 2.6621599842239364e-05,
"loss": 3.4926,
"step": 1427968
},
{
"epoch": 0.02,
"learning_rate": 2.6613213894728844e-05,
"loss": 3.4866,
"step": 1428480
},
{
"epoch": 0.02,
"learning_rate": 2.6604827947218324e-05,
"loss": 3.4953,
"step": 1428992
},
{
"epoch": 0.02,
"learning_rate": 2.6596458378511537e-05,
"loss": 3.4849,
"step": 1429504
},
{
"epoch": 0.02,
"learning_rate": 2.6588072431001017e-05,
"loss": 3.4946,
"step": 1430016
},
{
"epoch": 0.02,
"learning_rate": 2.6579686483490496e-05,
"loss": 3.4836,
"step": 1430528
},
{
"epoch": 0.02,
"learning_rate": 2.6571300535979976e-05,
"loss": 3.4875,
"step": 1431040
},
{
"epoch": 0.02,
"learning_rate": 2.6562930967273186e-05,
"loss": 3.4964,
"step": 1431552
},
{
"epoch": 0.02,
"learning_rate": 2.6554545019762665e-05,
"loss": 3.4907,
"step": 1432064
},
{
"epoch": 0.02,
"learning_rate": 2.6546159072252145e-05,
"loss": 3.5057,
"step": 1432576
},
{
"epoch": 0.02,
"learning_rate": 2.653777312474163e-05,
"loss": 3.5016,
"step": 1433088
},
{
"epoch": 0.02,
"learning_rate": 2.6529403556034838e-05,
"loss": 3.4932,
"step": 1433600
},
{
"epoch": 0.02,
"learning_rate": 2.6521017608524318e-05,
"loss": 3.4898,
"step": 1434112
},
{
"epoch": 0.02,
"learning_rate": 2.6512631661013798e-05,
"loss": 3.4936,
"step": 1434624
},
{
"epoch": 0.02,
"learning_rate": 2.6504245713503278e-05,
"loss": 3.4934,
"step": 1435136
},
{
"epoch": 0.02,
"learning_rate": 2.649587614479649e-05,
"loss": 3.4935,
"step": 1435648
},
{
"epoch": 0.02,
"learning_rate": 2.648749019728597e-05,
"loss": 3.4924,
"step": 1436160
},
{
"epoch": 0.02,
"learning_rate": 2.647910424977545e-05,
"loss": 3.4872,
"step": 1436672
},
{
"epoch": 0.02,
"learning_rate": 2.647071830226493e-05,
"loss": 3.4959,
"step": 1437184
},
{
"epoch": 0.02,
"learning_rate": 2.646234873355814e-05,
"loss": 3.4826,
"step": 1437696
},
{
"epoch": 0.02,
"learning_rate": 2.645396278604762e-05,
"loss": 3.4893,
"step": 1438208
},
{
"epoch": 0.02,
"learning_rate": 2.64455768385371e-05,
"loss": 3.4889,
"step": 1438720
},
{
"epoch": 0.02,
"learning_rate": 2.6437190891026582e-05,
"loss": 3.4881,
"step": 1439232
},
{
"epoch": 0.02,
"learning_rate": 2.642882132231979e-05,
"loss": 3.484,
"step": 1439744
},
{
"epoch": 0.02,
"learning_rate": 2.642043537480927e-05,
"loss": 3.5024,
"step": 1440256
},
{
"epoch": 0.02,
"learning_rate": 2.641204942729875e-05,
"loss": 3.5062,
"step": 1440768
},
{
"epoch": 0.02,
"learning_rate": 2.640366347978823e-05,
"loss": 3.4979,
"step": 1441280
},
{
"epoch": 0.02,
"learning_rate": 2.6395293911081444e-05,
"loss": 3.4809,
"step": 1441792
},
{
"epoch": 0.02,
"learning_rate": 2.6386907963570924e-05,
"loss": 3.4959,
"step": 1442304
},
{
"epoch": 0.02,
"learning_rate": 2.6378522016060404e-05,
"loss": 3.4928,
"step": 1442816
},
{
"epoch": 0.02,
"learning_rate": 2.6370136068549884e-05,
"loss": 3.4981,
"step": 1443328
},
{
"epoch": 0.02,
"learning_rate": 2.6361766499843093e-05,
"loss": 3.4938,
"step": 1443840
},
{
"epoch": 0.02,
"learning_rate": 2.6353380552332573e-05,
"loss": 3.4967,
"step": 1444352
},
{
"epoch": 0.02,
"learning_rate": 2.6344994604822053e-05,
"loss": 3.4903,
"step": 1444864
},
{
"epoch": 0.02,
"learning_rate": 2.6336608657311536e-05,
"loss": 3.4994,
"step": 1445376
},
{
"epoch": 0.02,
"learning_rate": 2.6328239088604745e-05,
"loss": 3.4927,
"step": 1445888
},
{
"epoch": 0.02,
"learning_rate": 2.6319853141094225e-05,
"loss": 3.4931,
"step": 1446400
},
{
"epoch": 0.02,
"learning_rate": 2.6311467193583705e-05,
"loss": 3.4927,
"step": 1446912
},
{
"epoch": 0.02,
"learning_rate": 2.6303081246073185e-05,
"loss": 3.4837,
"step": 1447424
},
{
"epoch": 0.02,
"learning_rate": 2.6294711677366398e-05,
"loss": 3.4994,
"step": 1447936
},
{
"epoch": 0.02,
"learning_rate": 2.6286325729855878e-05,
"loss": 3.4949,
"step": 1448448
},
{
"epoch": 0.02,
"learning_rate": 2.6277939782345357e-05,
"loss": 3.4945,
"step": 1448960
},
{
"epoch": 0.02,
"learning_rate": 2.6269553834834837e-05,
"loss": 3.485,
"step": 1449472
},
{
"epoch": 0.02,
"learning_rate": 2.6261184266128047e-05,
"loss": 3.4854,
"step": 1449984
},
{
"epoch": 0.03,
"eval_loss": 3.8504762649536133,
"eval_runtime": 303.0654,
"eval_samples_per_second": 1259.105,
"eval_steps_per_second": 39.348,
"step": 1450080
},
{
"epoch": 0.0,
"learning_rate": 2.6252798318617526e-05,
"loss": 3.4874,
"step": 1450496
},
{
"epoch": 0.0,
"learning_rate": 2.6244412371107006e-05,
"loss": 3.4851,
"step": 1451008
},
{
"epoch": 0.0,
"learning_rate": 2.6236026423596483e-05,
"loss": 3.4923,
"step": 1451520
},
{
"epoch": 0.0,
"learning_rate": 2.6227640476085963e-05,
"loss": 3.4927,
"step": 1452032
},
{
"epoch": 0.0,
"learning_rate": 2.621927090737918e-05,
"loss": 3.5041,
"step": 1452544
},
{
"epoch": 0.0,
"learning_rate": 2.621088495986866e-05,
"loss": 3.4838,
"step": 1453056
},
{
"epoch": 0.0,
"learning_rate": 2.6202499012358135e-05,
"loss": 3.4846,
"step": 1453568
},
{
"epoch": 0.0,
"learning_rate": 2.6194113064847615e-05,
"loss": 3.4776,
"step": 1454080
},
{
"epoch": 0.0,
"learning_rate": 2.618574349614083e-05,
"loss": 3.4952,
"step": 1454592
},
{
"epoch": 0.0,
"learning_rate": 2.6177357548630304e-05,
"loss": 3.4915,
"step": 1455104
},
{
"epoch": 0.0,
"learning_rate": 2.6168971601119784e-05,
"loss": 3.4939,
"step": 1455616
},
{
"epoch": 0.0,
"learning_rate": 2.6160585653609264e-05,
"loss": 3.4882,
"step": 1456128
},
{
"epoch": 0.0,
"learning_rate": 2.615221608490248e-05,
"loss": 3.4835,
"step": 1456640
},
{
"epoch": 0.0,
"learning_rate": 2.6143830137391957e-05,
"loss": 3.482,
"step": 1457152
},
{
"epoch": 0.0,
"learning_rate": 2.6135444189881437e-05,
"loss": 3.4775,
"step": 1457664
},
{
"epoch": 0.0,
"learning_rate": 2.6127058242370917e-05,
"loss": 3.483,
"step": 1458176
},
{
"epoch": 0.0,
"learning_rate": 2.6118688673664132e-05,
"loss": 3.4865,
"step": 1458688
},
{
"epoch": 0.0,
"learning_rate": 2.6110302726153606e-05,
"loss": 3.4835,
"step": 1459200
},
{
"epoch": 0.0,
"learning_rate": 2.610191677864309e-05,
"loss": 3.4836,
"step": 1459712
},
{
"epoch": 0.0,
"learning_rate": 2.609353083113257e-05,
"loss": 3.5066,
"step": 1460224
},
{
"epoch": 0.0,
"learning_rate": 2.6085161262425778e-05,
"loss": 3.4871,
"step": 1460736
},
{
"epoch": 0.0,
"learning_rate": 2.6076775314915258e-05,
"loss": 3.4914,
"step": 1461248
},
{
"epoch": 0.0,
"learning_rate": 2.6068389367404738e-05,
"loss": 3.4891,
"step": 1461760
},
{
"epoch": 0.0,
"learning_rate": 2.6060003419894218e-05,
"loss": 3.4934,
"step": 1462272
},
{
"epoch": 0.0,
"learning_rate": 2.605163385118743e-05,
"loss": 3.4784,
"step": 1462784
},
{
"epoch": 0.0,
"learning_rate": 2.604324790367691e-05,
"loss": 3.4949,
"step": 1463296
},
{
"epoch": 0.0,
"learning_rate": 2.603486195616639e-05,
"loss": 3.4836,
"step": 1463808
},
{
"epoch": 0.0,
"learning_rate": 2.602647600865587e-05,
"loss": 3.4851,
"step": 1464320
},
{
"epoch": 0.0,
"learning_rate": 2.601810643994908e-05,
"loss": 3.4717,
"step": 1464832
},
{
"epoch": 0.01,
"learning_rate": 2.600972049243856e-05,
"loss": 3.4797,
"step": 1465344
},
{
"epoch": 0.01,
"learning_rate": 2.6001334544928043e-05,
"loss": 3.4849,
"step": 1465856
},
{
"epoch": 0.01,
"learning_rate": 2.5992948597417523e-05,
"loss": 3.4905,
"step": 1466368
},
{
"epoch": 0.01,
"learning_rate": 2.5984579028710732e-05,
"loss": 3.4958,
"step": 1466880
},
{
"epoch": 0.01,
"learning_rate": 2.597619308120021e-05,
"loss": 3.4918,
"step": 1467392
},
{
"epoch": 0.01,
"learning_rate": 2.596780713368969e-05,
"loss": 3.4812,
"step": 1467904
},
{
"epoch": 0.01,
"learning_rate": 2.595942118617917e-05,
"loss": 3.4949,
"step": 1468416
},
{
"epoch": 0.01,
"learning_rate": 2.5951051617472384e-05,
"loss": 3.4794,
"step": 1468928
},
{
"epoch": 0.01,
"learning_rate": 2.5942665669961864e-05,
"loss": 3.4877,
"step": 1469440
},
{
"epoch": 0.01,
"learning_rate": 2.5934279722451344e-05,
"loss": 3.4736,
"step": 1469952
},
{
"epoch": 0.01,
"learning_rate": 2.5925893774940824e-05,
"loss": 3.4861,
"step": 1470464
},
{
"epoch": 0.01,
"learning_rate": 2.5917524206234033e-05,
"loss": 3.4787,
"step": 1470976
},
{
"epoch": 0.01,
"learning_rate": 2.5909138258723513e-05,
"loss": 3.4924,
"step": 1471488
},
{
"epoch": 0.01,
"learning_rate": 2.5900752311212993e-05,
"loss": 3.4857,
"step": 1472000
},
{
"epoch": 0.01,
"learning_rate": 2.5892366363702476e-05,
"loss": 3.4774,
"step": 1472512
},
{
"epoch": 0.01,
"learning_rate": 2.5883996794995685e-05,
"loss": 3.493,
"step": 1473024
},
{
"epoch": 0.01,
"learning_rate": 2.5875610847485165e-05,
"loss": 3.4823,
"step": 1473536
},
{
"epoch": 0.01,
"learning_rate": 2.5867224899974645e-05,
"loss": 3.4803,
"step": 1474048
},
{
"epoch": 0.01,
"learning_rate": 2.5858838952464125e-05,
"loss": 3.4689,
"step": 1474560
},
{
"epoch": 0.01,
"learning_rate": 2.5850453004953605e-05,
"loss": 3.4795,
"step": 1475072
},
{
"epoch": 0.01,
"learning_rate": 2.5842083436246818e-05,
"loss": 3.4876,
"step": 1475584
},
{
"epoch": 0.01,
"learning_rate": 2.5833697488736298e-05,
"loss": 3.4843,
"step": 1476096
},
{
"epoch": 0.01,
"learning_rate": 2.5825311541225778e-05,
"loss": 3.4802,
"step": 1476608
},
{
"epoch": 0.01,
"learning_rate": 2.5816925593715258e-05,
"loss": 3.4716,
"step": 1477120
},
{
"epoch": 0.01,
"learning_rate": 2.5808556025008467e-05,
"loss": 3.4813,
"step": 1477632
},
{
"epoch": 0.01,
"learning_rate": 2.5800170077497947e-05,
"loss": 3.4691,
"step": 1478144
},
{
"epoch": 0.01,
"learning_rate": 2.579178412998743e-05,
"loss": 3.4913,
"step": 1478656
},
{
"epoch": 0.01,
"learning_rate": 2.578339818247691e-05,
"loss": 3.4797,
"step": 1479168
},
{
"epoch": 0.01,
"learning_rate": 2.577502861377012e-05,
"loss": 3.4837,
"step": 1479680
},
{
"epoch": 0.01,
"learning_rate": 2.57666426662596e-05,
"loss": 3.4854,
"step": 1480192
},
{
"epoch": 0.01,
"learning_rate": 2.575825671874908e-05,
"loss": 3.4704,
"step": 1480704
},
{
"epoch": 0.01,
"learning_rate": 2.574987077123856e-05,
"loss": 3.4755,
"step": 1481216
},
{
"epoch": 0.01,
"learning_rate": 2.574150120253177e-05,
"loss": 3.484,
"step": 1481728
},
{
"epoch": 0.01,
"learning_rate": 2.573311525502125e-05,
"loss": 3.4732,
"step": 1482240
},
{
"epoch": 0.01,
"learning_rate": 2.572472930751073e-05,
"loss": 3.4793,
"step": 1482752
},
{
"epoch": 0.01,
"learning_rate": 2.571634336000021e-05,
"loss": 3.4798,
"step": 1483264
},
{
"epoch": 0.01,
"learning_rate": 2.570797379129342e-05,
"loss": 3.4856,
"step": 1483776
},
{
"epoch": 0.01,
"learning_rate": 2.56995878437829e-05,
"loss": 3.47,
"step": 1484288
},
{
"epoch": 0.01,
"learning_rate": 2.5691201896272384e-05,
"loss": 3.4774,
"step": 1484800
},
{
"epoch": 0.01,
"learning_rate": 2.5682815948761864e-05,
"loss": 3.4695,
"step": 1485312
},
{
"epoch": 0.01,
"learning_rate": 2.5674446380055073e-05,
"loss": 3.4768,
"step": 1485824
},
{
"epoch": 0.01,
"learning_rate": 2.5666060432544553e-05,
"loss": 3.4898,
"step": 1486336
},
{
"epoch": 0.01,
"learning_rate": 2.5657674485034033e-05,
"loss": 3.4788,
"step": 1486848
},
{
"epoch": 0.01,
"learning_rate": 2.5649288537523513e-05,
"loss": 3.4928,
"step": 1487360
},
{
"epoch": 0.01,
"learning_rate": 2.5640918968816725e-05,
"loss": 3.489,
"step": 1487872
},
{
"epoch": 0.01,
"learning_rate": 2.5632533021306205e-05,
"loss": 3.4906,
"step": 1488384
},
{
"epoch": 0.01,
"learning_rate": 2.5624147073795685e-05,
"loss": 3.4716,
"step": 1488896
},
{
"epoch": 0.01,
"learning_rate": 2.5615761126285165e-05,
"loss": 3.4886,
"step": 1489408
},
{
"epoch": 0.01,
"learning_rate": 2.5607375178774645e-05,
"loss": 3.4892,
"step": 1489920
},
{
"epoch": 0.01,
"learning_rate": 2.5599005610067854e-05,
"loss": 3.4805,
"step": 1490432
},
{
"epoch": 0.01,
"learning_rate": 2.5590619662557337e-05,
"loss": 3.4841,
"step": 1490944
},
{
"epoch": 0.01,
"learning_rate": 2.5582233715046817e-05,
"loss": 3.4857,
"step": 1491456
},
{
"epoch": 0.01,
"learning_rate": 2.5573847767536297e-05,
"loss": 3.4981,
"step": 1491968
},
{
"epoch": 0.01,
"learning_rate": 2.5565478198829506e-05,
"loss": 3.4805,
"step": 1492480
},
{
"epoch": 0.01,
"learning_rate": 2.5557092251318986e-05,
"loss": 3.4685,
"step": 1492992
},
{
"epoch": 0.01,
"learning_rate": 2.5548706303808466e-05,
"loss": 3.4766,
"step": 1493504
},
{
"epoch": 0.01,
"learning_rate": 2.554033673510168e-05,
"loss": 3.4823,
"step": 1494016
},
{
"epoch": 0.01,
"learning_rate": 2.553195078759116e-05,
"loss": 3.4872,
"step": 1494528
},
{
"epoch": 0.01,
"learning_rate": 2.552356484008064e-05,
"loss": 3.4875,
"step": 1495040
},
{
"epoch": 0.01,
"learning_rate": 2.551517889257012e-05,
"loss": 3.4793,
"step": 1495552
},
{
"epoch": 0.02,
"learning_rate": 2.5506809323863328e-05,
"loss": 3.4814,
"step": 1496064
},
{
"epoch": 0.02,
"learning_rate": 2.5498423376352808e-05,
"loss": 3.4691,
"step": 1496576
},
{
"epoch": 0.02,
"learning_rate": 2.549003742884229e-05,
"loss": 3.4771,
"step": 1497088
},
{
"epoch": 0.02,
"learning_rate": 2.548165148133177e-05,
"loss": 3.4804,
"step": 1497600
},
{
"epoch": 0.02,
"learning_rate": 2.547328191262498e-05,
"loss": 3.4903,
"step": 1498112
},
{
"epoch": 0.02,
"learning_rate": 2.546489596511446e-05,
"loss": 3.5032,
"step": 1498624
},
{
"epoch": 0.02,
"learning_rate": 2.545651001760394e-05,
"loss": 3.4831,
"step": 1499136
},
{
"epoch": 0.02,
"learning_rate": 2.544812407009342e-05,
"loss": 3.4718,
"step": 1499648
},
{
"epoch": 0.02,
"learning_rate": 2.54397381225829e-05,
"loss": 3.4858,
"step": 1500160
},
{
"epoch": 0.02,
"learning_rate": 2.5431368553876112e-05,
"loss": 3.477,
"step": 1500672
},
{
"epoch": 0.02,
"learning_rate": 2.5422982606365592e-05,
"loss": 3.4886,
"step": 1501184
},
{
"epoch": 0.02,
"learning_rate": 2.5414596658855072e-05,
"loss": 3.4795,
"step": 1501696
},
{
"epoch": 0.02,
"learning_rate": 2.5406210711344552e-05,
"loss": 3.4799,
"step": 1502208
},
{
"epoch": 0.02,
"learning_rate": 2.539784114263776e-05,
"loss": 3.4819,
"step": 1502720
},
{
"epoch": 0.02,
"learning_rate": 2.5389455195127245e-05,
"loss": 3.4898,
"step": 1503232
},
{
"epoch": 0.02,
"learning_rate": 2.5381069247616725e-05,
"loss": 3.4669,
"step": 1503744
},
{
"epoch": 0.02,
"learning_rate": 2.5372683300106205e-05,
"loss": 3.4789,
"step": 1504256
},
{
"epoch": 0.02,
"learning_rate": 2.5364313731399414e-05,
"loss": 3.4722,
"step": 1504768
},
{
"epoch": 0.02,
"learning_rate": 2.5355927783888894e-05,
"loss": 3.4867,
"step": 1505280
},
{
"epoch": 0.02,
"learning_rate": 2.5347541836378374e-05,
"loss": 3.4724,
"step": 1505792
},
{
"epoch": 0.02,
"learning_rate": 2.5339155888867854e-05,
"loss": 3.4832,
"step": 1506304
},
{
"epoch": 0.02,
"learning_rate": 2.5330786320161066e-05,
"loss": 3.4736,
"step": 1506816
},
{
"epoch": 0.02,
"learning_rate": 2.5322400372650546e-05,
"loss": 3.4772,
"step": 1507328
},
{
"epoch": 0.02,
"learning_rate": 2.5314014425140026e-05,
"loss": 3.4809,
"step": 1507840
},
{
"epoch": 0.02,
"learning_rate": 2.5305644856433235e-05,
"loss": 3.4825,
"step": 1508352
},
{
"epoch": 0.02,
"learning_rate": 2.5297258908922715e-05,
"loss": 3.4906,
"step": 1508864
},
{
"epoch": 0.02,
"learning_rate": 2.52888729614122e-05,
"loss": 3.4921,
"step": 1509376
},
{
"epoch": 0.02,
"learning_rate": 2.5280487013901678e-05,
"loss": 3.481,
"step": 1509888
},
{
"epoch": 0.02,
"learning_rate": 2.5272101066391158e-05,
"loss": 3.4762,
"step": 1510400
},
{
"epoch": 0.02,
"learning_rate": 2.5263731497684367e-05,
"loss": 3.4809,
"step": 1510912
},
{
"epoch": 0.02,
"learning_rate": 2.5255345550173847e-05,
"loss": 3.4828,
"step": 1511424
},
{
"epoch": 0.02,
"learning_rate": 2.5246959602663327e-05,
"loss": 3.476,
"step": 1511936
},
{
"epoch": 0.02,
"learning_rate": 2.5238573655152804e-05,
"loss": 3.4797,
"step": 1512448
},
{
"epoch": 0.02,
"learning_rate": 2.523020408644602e-05,
"loss": 3.4809,
"step": 1512960
},
{
"epoch": 0.02,
"learning_rate": 2.52218181389355e-05,
"loss": 3.4794,
"step": 1513472
},
{
"epoch": 0.02,
"learning_rate": 2.521343219142498e-05,
"loss": 3.4745,
"step": 1513984
},
{
"epoch": 0.02,
"learning_rate": 2.5205046243914453e-05,
"loss": 3.4753,
"step": 1514496
},
{
"epoch": 0.02,
"learning_rate": 2.519667667520767e-05,
"loss": 3.4742,
"step": 1515008
},
{
"epoch": 0.02,
"learning_rate": 2.518829072769715e-05,
"loss": 3.4794,
"step": 1515520
},
{
"epoch": 0.02,
"learning_rate": 2.5179904780186632e-05,
"loss": 3.4708,
"step": 1516032
},
{
"epoch": 0.02,
"learning_rate": 2.5171518832676105e-05,
"loss": 3.4922,
"step": 1516544
},
{
"epoch": 0.02,
"learning_rate": 2.516314926396932e-05,
"loss": 3.4902,
"step": 1517056
},
{
"epoch": 0.02,
"learning_rate": 2.51547633164588e-05,
"loss": 3.4893,
"step": 1517568
},
{
"epoch": 0.02,
"learning_rate": 2.5146377368948278e-05,
"loss": 3.4687,
"step": 1518080
},
{
"epoch": 0.02,
"learning_rate": 2.5137991421437757e-05,
"loss": 3.4821,
"step": 1518592
},
{
"epoch": 0.02,
"learning_rate": 2.5129621852730973e-05,
"loss": 3.4859,
"step": 1519104
},
{
"epoch": 0.02,
"learning_rate": 2.5121235905220453e-05,
"loss": 3.4823,
"step": 1519616
},
{
"epoch": 0.02,
"learning_rate": 2.5112849957709926e-05,
"loss": 3.4844,
"step": 1520128
},
{
"epoch": 0.02,
"learning_rate": 2.5104464010199406e-05,
"loss": 3.4833,
"step": 1520640
},
{
"epoch": 0.02,
"learning_rate": 2.5096094441492622e-05,
"loss": 3.4804,
"step": 1521152
},
{
"epoch": 0.02,
"learning_rate": 2.5087708493982102e-05,
"loss": 3.4882,
"step": 1521664
},
{
"epoch": 0.02,
"learning_rate": 2.507932254647158e-05,
"loss": 3.4815,
"step": 1522176
},
{
"epoch": 0.02,
"learning_rate": 2.507093659896106e-05,
"loss": 3.4815,
"step": 1522688
},
{
"epoch": 0.02,
"learning_rate": 2.5062567030254275e-05,
"loss": 3.4796,
"step": 1523200
},
{
"epoch": 0.02,
"learning_rate": 2.505418108274375e-05,
"loss": 3.4699,
"step": 1523712
},
{
"epoch": 0.02,
"learning_rate": 2.504579513523323e-05,
"loss": 3.4877,
"step": 1524224
},
{
"epoch": 0.02,
"learning_rate": 2.503740918772271e-05,
"loss": 3.4845,
"step": 1524736
},
{
"epoch": 0.02,
"learning_rate": 2.5029039619015927e-05,
"loss": 3.4843,
"step": 1525248
},
{
"epoch": 0.02,
"learning_rate": 2.50206536715054e-05,
"loss": 3.4697,
"step": 1525760
},
{
"epoch": 0.02,
"learning_rate": 2.501226772399488e-05,
"loss": 3.4724,
"step": 1526272
},
{
"epoch": 0.03,
"eval_loss": 3.8520138263702393,
"eval_runtime": 312.0025,
"eval_samples_per_second": 1223.038,
"eval_steps_per_second": 38.221,
"step": 1526400
},
{
"epoch": 1.0,
"learning_rate": 2.500388177648436e-05,
"loss": 3.4807,
"step": 1526784
},
{
"epoch": 1.0,
"learning_rate": 2.4995512207777576e-05,
"loss": 3.4714,
"step": 1527296
},
{
"epoch": 1.0,
"learning_rate": 2.4987126260267056e-05,
"loss": 3.4801,
"step": 1527808
},
{
"epoch": 1.0,
"learning_rate": 2.4978740312756536e-05,
"loss": 3.4818,
"step": 1528320
},
{
"epoch": 1.0,
"learning_rate": 2.4970354365246016e-05,
"loss": 3.4954,
"step": 1528832
},
{
"epoch": 1.0,
"learning_rate": 2.4961984796539225e-05,
"loss": 3.4711,
"step": 1529344
},
{
"epoch": 1.0,
"learning_rate": 2.4953598849028705e-05,
"loss": 3.4711,
"step": 1529856
},
{
"epoch": 1.0,
"learning_rate": 2.4945212901518185e-05,
"loss": 3.4641,
"step": 1530368
},
{
"epoch": 1.0,
"learning_rate": 2.4936826954007665e-05,
"loss": 3.483,
"step": 1530880
},
{
"epoch": 1.0,
"learning_rate": 2.4928457385300877e-05,
"loss": 3.4805,
"step": 1531392
},
{
"epoch": 1.0,
"learning_rate": 2.4920071437790357e-05,
"loss": 3.4767,
"step": 1531904
},
{
"epoch": 1.0,
"learning_rate": 2.4911685490279837e-05,
"loss": 3.4796,
"step": 1532416
},
{
"epoch": 1.0,
"learning_rate": 2.4903299542769314e-05,
"loss": 3.4707,
"step": 1532928
},
{
"epoch": 1.0,
"learning_rate": 2.489492997406253e-05,
"loss": 3.4772,
"step": 1533440
},
{
"epoch": 1.0,
"learning_rate": 2.488654402655201e-05,
"loss": 3.4635,
"step": 1533952
},
{
"epoch": 1.0,
"learning_rate": 2.487815807904149e-05,
"loss": 3.4753,
"step": 1534464
},
{
"epoch": 1.0,
"learning_rate": 2.4869772131530966e-05,
"loss": 3.4708,
"step": 1534976
},
{
"epoch": 1.0,
"learning_rate": 2.486140256282418e-05,
"loss": 3.4726,
"step": 1535488
},
{
"epoch": 1.0,
"learning_rate": 2.485301661531366e-05,
"loss": 3.4752,
"step": 1536000
},
{
"epoch": 1.0,
"learning_rate": 2.484463066780314e-05,
"loss": 3.492,
"step": 1536512
},
{
"epoch": 1.0,
"learning_rate": 2.483624472029262e-05,
"loss": 3.4741,
"step": 1537024
},
{
"epoch": 1.0,
"learning_rate": 2.482787515158583e-05,
"loss": 3.4784,
"step": 1537536
},
{
"epoch": 1.0,
"learning_rate": 2.481948920407531e-05,
"loss": 3.4763,
"step": 1538048
},
{
"epoch": 1.0,
"learning_rate": 2.4811103256564787e-05,
"loss": 3.4812,
"step": 1538560
},
{
"epoch": 1.0,
"learning_rate": 2.4802717309054267e-05,
"loss": 3.4694,
"step": 1539072
},
{
"epoch": 1.0,
"learning_rate": 2.4794347740347483e-05,
"loss": 3.4801,
"step": 1539584
},
{
"epoch": 1.0,
"learning_rate": 2.4785961792836963e-05,
"loss": 3.4735,
"step": 1540096
},
{
"epoch": 1.0,
"learning_rate": 2.477757584532644e-05,
"loss": 3.4694,
"step": 1540608
},
{
"epoch": 1.0,
"learning_rate": 2.476918989781592e-05,
"loss": 3.4639,
"step": 1541120
},
{
"epoch": 1.0,
"learning_rate": 2.4760820329109132e-05,
"loss": 3.4684,
"step": 1541632
},
{
"epoch": 1.01,
"learning_rate": 2.475243438159861e-05,
"loss": 3.4724,
"step": 1542144
},
{
"epoch": 1.01,
"learning_rate": 2.4744048434088092e-05,
"loss": 3.4797,
"step": 1542656
},
{
"epoch": 1.01,
"learning_rate": 2.4735662486577572e-05,
"loss": 3.483,
"step": 1543168
},
{
"epoch": 1.01,
"learning_rate": 2.4727292917870785e-05,
"loss": 3.4771,
"step": 1543680
},
{
"epoch": 1.01,
"learning_rate": 2.471890697036026e-05,
"loss": 3.4702,
"step": 1544192
},
{
"epoch": 1.01,
"learning_rate": 2.471052102284974e-05,
"loss": 3.4846,
"step": 1544704
},
{
"epoch": 1.01,
"learning_rate": 2.470213507533922e-05,
"loss": 3.4727,
"step": 1545216
},
{
"epoch": 1.01,
"learning_rate": 2.46937491278287e-05,
"loss": 3.4738,
"step": 1545728
},
{
"epoch": 1.01,
"learning_rate": 2.4685379559121914e-05,
"loss": 3.4597,
"step": 1546240
},
{
"epoch": 1.01,
"learning_rate": 2.4676993611611393e-05,
"loss": 3.4723,
"step": 1546752
},
{
"epoch": 1.01,
"learning_rate": 2.4668607664100873e-05,
"loss": 3.4689,
"step": 1547264
},
{
"epoch": 1.01,
"learning_rate": 2.4660238095394083e-05,
"loss": 3.4831,
"step": 1547776
},
{
"epoch": 1.01,
"learning_rate": 2.4651852147883562e-05,
"loss": 3.474,
"step": 1548288
},
{
"epoch": 1.01,
"learning_rate": 2.4643466200373046e-05,
"loss": 3.4643,
"step": 1548800
},
{
"epoch": 1.01,
"learning_rate": 2.4635080252862526e-05,
"loss": 3.4817,
"step": 1549312
},
{
"epoch": 1.01,
"learning_rate": 2.4626710684155735e-05,
"loss": 3.4708,
"step": 1549824
},
{
"epoch": 1.01,
"learning_rate": 2.4618324736645215e-05,
"loss": 3.4666,
"step": 1550336
},
{
"epoch": 1.01,
"learning_rate": 2.4609938789134695e-05,
"loss": 3.4624,
"step": 1550848
},
{
"epoch": 1.01,
"learning_rate": 2.4601552841624175e-05,
"loss": 3.4627,
"step": 1551360
},
{
"epoch": 1.01,
"learning_rate": 2.4593183272917387e-05,
"loss": 3.4756,
"step": 1551872
},
{
"epoch": 1.01,
"learning_rate": 2.4584797325406867e-05,
"loss": 3.4725,
"step": 1552384
},
{
"epoch": 1.01,
"learning_rate": 2.4576411377896347e-05,
"loss": 3.4679,
"step": 1552896
},
{
"epoch": 1.01,
"learning_rate": 2.4568025430385827e-05,
"loss": 3.461,
"step": 1553408
},
{
"epoch": 1.01,
"learning_rate": 2.4559639482875307e-05,
"loss": 3.472,
"step": 1553920
},
{
"epoch": 1.01,
"learning_rate": 2.4551269914168516e-05,
"loss": 3.4584,
"step": 1554432
},
{
"epoch": 1.01,
"learning_rate": 2.4542883966658e-05,
"loss": 3.4759,
"step": 1554944
},
{
"epoch": 1.01,
"learning_rate": 2.453449801914748e-05,
"loss": 3.4639,
"step": 1555456
},
{
"epoch": 1.01,
"learning_rate": 2.452611207163696e-05,
"loss": 3.4754,
"step": 1555968
},
{
"epoch": 1.01,
"learning_rate": 2.451774250293017e-05,
"loss": 3.4696,
"step": 1556480
},
{
"epoch": 1.01,
"learning_rate": 2.450935655541965e-05,
"loss": 3.4668,
"step": 1556992
},
{
"epoch": 1.01,
"learning_rate": 2.450097060790913e-05,
"loss": 3.4636,
"step": 1557504
},
{
"epoch": 1.01,
"learning_rate": 2.449258466039861e-05,
"loss": 3.4741,
"step": 1558016
},
{
"epoch": 1.01,
"learning_rate": 2.448421509169182e-05,
"loss": 3.4601,
"step": 1558528
},
{
"epoch": 1.01,
"learning_rate": 2.44758291441813e-05,
"loss": 3.4665,
"step": 1559040
},
{
"epoch": 1.01,
"learning_rate": 2.446744319667078e-05,
"loss": 3.4737,
"step": 1559552
},
{
"epoch": 1.01,
"learning_rate": 2.445905724916026e-05,
"loss": 3.4721,
"step": 1560064
},
{
"epoch": 1.01,
"learning_rate": 2.445068768045347e-05,
"loss": 3.4608,
"step": 1560576
},
{
"epoch": 1.01,
"learning_rate": 2.4442301732942953e-05,
"loss": 3.4628,
"step": 1561088
},
{
"epoch": 1.01,
"learning_rate": 2.4433915785432433e-05,
"loss": 3.4628,
"step": 1561600
},
{
"epoch": 1.01,
"learning_rate": 2.4425529837921913e-05,
"loss": 3.4627,
"step": 1562112
},
{
"epoch": 1.01,
"learning_rate": 2.4417160269215122e-05,
"loss": 3.4775,
"step": 1562624
},
{
"epoch": 1.01,
"learning_rate": 2.4408774321704602e-05,
"loss": 3.4697,
"step": 1563136
},
{
"epoch": 1.01,
"learning_rate": 2.4400388374194082e-05,
"loss": 3.4804,
"step": 1563648
},
{
"epoch": 1.01,
"learning_rate": 2.4392002426683562e-05,
"loss": 3.4782,
"step": 1564160
},
{
"epoch": 1.01,
"learning_rate": 2.4383632857976775e-05,
"loss": 3.483,
"step": 1564672
},
{
"epoch": 1.01,
"learning_rate": 2.4375246910466254e-05,
"loss": 3.4622,
"step": 1565184
},
{
"epoch": 1.01,
"learning_rate": 2.4366860962955734e-05,
"loss": 3.4696,
"step": 1565696
},
{
"epoch": 1.01,
"learning_rate": 2.435847501544521e-05,
"loss": 3.4822,
"step": 1566208
},
{
"epoch": 1.01,
"learning_rate": 2.4350105446738423e-05,
"loss": 3.4681,
"step": 1566720
},
{
"epoch": 1.01,
"learning_rate": 2.4341719499227907e-05,
"loss": 3.4697,
"step": 1567232
},
{
"epoch": 1.01,
"learning_rate": 2.4333333551717387e-05,
"loss": 3.473,
"step": 1567744
},
{
"epoch": 1.01,
"learning_rate": 2.4324947604206863e-05,
"loss": 3.4879,
"step": 1568256
},
{
"epoch": 1.01,
"learning_rate": 2.4316578035500076e-05,
"loss": 3.4697,
"step": 1568768
},
{
"epoch": 1.01,
"learning_rate": 2.4308192087989556e-05,
"loss": 3.4559,
"step": 1569280
},
{
"epoch": 1.01,
"learning_rate": 2.4299806140479036e-05,
"loss": 3.4632,
"step": 1569792
},
{
"epoch": 1.01,
"learning_rate": 2.4291420192968516e-05,
"loss": 3.4709,
"step": 1570304
},
{
"epoch": 1.01,
"learning_rate": 2.4283050624261728e-05,
"loss": 3.4768,
"step": 1570816
},
{
"epoch": 1.01,
"learning_rate": 2.4274664676751208e-05,
"loss": 3.4769,
"step": 1571328
},
{
"epoch": 1.01,
"learning_rate": 2.4266278729240685e-05,
"loss": 3.4686,
"step": 1571840
},
{
"epoch": 1.02,
"learning_rate": 2.4257892781730165e-05,
"loss": 3.4691,
"step": 1572352
},
{
"epoch": 1.02,
"learning_rate": 2.4249523213023377e-05,
"loss": 3.4619,
"step": 1572864
},
{
"epoch": 1.02,
"learning_rate": 2.4241137265512857e-05,
"loss": 3.4611,
"step": 1573376
},
{
"epoch": 1.02,
"learning_rate": 2.4232751318002337e-05,
"loss": 3.4701,
"step": 1573888
},
{
"epoch": 1.02,
"learning_rate": 2.4224365370491817e-05,
"loss": 3.4766,
"step": 1574400
},
{
"epoch": 1.02,
"learning_rate": 2.421599580178503e-05,
"loss": 3.4909,
"step": 1574912
},
{
"epoch": 1.02,
"learning_rate": 2.4207609854274506e-05,
"loss": 3.475,
"step": 1575424
},
{
"epoch": 1.02,
"learning_rate": 2.4199223906763986e-05,
"loss": 3.4594,
"step": 1575936
},
{
"epoch": 1.02,
"learning_rate": 2.419083795925347e-05,
"loss": 3.474,
"step": 1576448
},
{
"epoch": 1.02,
"learning_rate": 2.4182468390546682e-05,
"loss": 3.4624,
"step": 1576960
},
{
"epoch": 1.02,
"learning_rate": 2.417408244303616e-05,
"loss": 3.4785,
"step": 1577472
},
{
"epoch": 1.02,
"learning_rate": 2.416569649552564e-05,
"loss": 3.4732,
"step": 1577984
},
{
"epoch": 1.02,
"learning_rate": 2.415731054801512e-05,
"loss": 3.4661,
"step": 1578496
},
{
"epoch": 1.02,
"learning_rate": 2.414894097930833e-05,
"loss": 3.4683,
"step": 1579008
},
{
"epoch": 1.02,
"learning_rate": 2.414055503179781e-05,
"loss": 3.4775,
"step": 1579520
},
{
"epoch": 1.02,
"learning_rate": 2.413216908428729e-05,
"loss": 3.4577,
"step": 1580032
},
{
"epoch": 1.02,
"learning_rate": 2.412378313677677e-05,
"loss": 3.4675,
"step": 1580544
},
{
"epoch": 1.02,
"learning_rate": 2.411541356806998e-05,
"loss": 3.458,
"step": 1581056
},
{
"epoch": 1.02,
"learning_rate": 2.410702762055946e-05,
"loss": 3.4763,
"step": 1581568
},
{
"epoch": 1.02,
"learning_rate": 2.409864167304894e-05,
"loss": 3.4638,
"step": 1582080
},
{
"epoch": 1.02,
"learning_rate": 2.4090255725538423e-05,
"loss": 3.466,
"step": 1582592
},
{
"epoch": 1.02,
"learning_rate": 2.4081886156831632e-05,
"loss": 3.4618,
"step": 1583104
},
{
"epoch": 1.02,
"learning_rate": 2.4073500209321112e-05,
"loss": 3.4677,
"step": 1583616
},
{
"epoch": 1.02,
"learning_rate": 2.4065114261810592e-05,
"loss": 3.4687,
"step": 1584128
},
{
"epoch": 1.02,
"learning_rate": 2.4056728314300072e-05,
"loss": 3.4702,
"step": 1584640
},
{
"epoch": 1.02,
"learning_rate": 2.4048358745593284e-05,
"loss": 3.477,
"step": 1585152
},
{
"epoch": 1.02,
"learning_rate": 2.4039972798082764e-05,
"loss": 3.4793,
"step": 1585664
},
{
"epoch": 1.02,
"learning_rate": 2.4031586850572244e-05,
"loss": 3.4715,
"step": 1586176
},
{
"epoch": 1.02,
"learning_rate": 2.4023200903061724e-05,
"loss": 3.4653,
"step": 1586688
},
{
"epoch": 1.02,
"learning_rate": 2.4014831334354933e-05,
"loss": 3.4686,
"step": 1587200
},
{
"epoch": 1.02,
"learning_rate": 2.4006445386844413e-05,
"loss": 3.4752,
"step": 1587712
},
{
"epoch": 1.02,
"learning_rate": 2.3998059439333893e-05,
"loss": 3.4589,
"step": 1588224
},
{
"epoch": 1.02,
"learning_rate": 2.3989673491823377e-05,
"loss": 3.4701,
"step": 1588736
},
{
"epoch": 1.02,
"learning_rate": 2.3981303923116586e-05,
"loss": 3.4627,
"step": 1589248
},
{
"epoch": 1.02,
"learning_rate": 2.3972917975606066e-05,
"loss": 3.4705,
"step": 1589760
},
{
"epoch": 1.02,
"learning_rate": 2.3964532028095546e-05,
"loss": 3.4652,
"step": 1590272
},
{
"epoch": 1.02,
"learning_rate": 2.3956146080585026e-05,
"loss": 3.4649,
"step": 1590784
},
{
"epoch": 1.02,
"learning_rate": 2.3947776511878238e-05,
"loss": 3.4595,
"step": 1591296
},
{
"epoch": 1.02,
"learning_rate": 2.3939390564367718e-05,
"loss": 3.4683,
"step": 1591808
},
{
"epoch": 1.02,
"learning_rate": 2.3931004616857198e-05,
"loss": 3.4605,
"step": 1592320
},
{
"epoch": 1.02,
"learning_rate": 2.3922618669346678e-05,
"loss": 3.4793,
"step": 1592832
},
{
"epoch": 1.02,
"learning_rate": 2.3914249100639887e-05,
"loss": 3.4735,
"step": 1593344
},
{
"epoch": 1.02,
"learning_rate": 2.3905863153129367e-05,
"loss": 3.485,
"step": 1593856
},
{
"epoch": 1.02,
"learning_rate": 2.3897477205618847e-05,
"loss": 3.4529,
"step": 1594368
},
{
"epoch": 1.02,
"learning_rate": 2.388909125810833e-05,
"loss": 3.4725,
"step": 1594880
},
{
"epoch": 1.02,
"learning_rate": 2.388072168940154e-05,
"loss": 3.4747,
"step": 1595392
},
{
"epoch": 1.02,
"learning_rate": 2.387233574189102e-05,
"loss": 3.4703,
"step": 1595904
},
{
"epoch": 1.02,
"learning_rate": 2.38639497943805e-05,
"loss": 3.4738,
"step": 1596416
},
{
"epoch": 1.02,
"learning_rate": 2.385556384686998e-05,
"loss": 3.4728,
"step": 1596928
},
{
"epoch": 1.02,
"learning_rate": 2.3847194278163192e-05,
"loss": 3.4676,
"step": 1597440
},
{
"epoch": 1.02,
"learning_rate": 2.3838808330652672e-05,
"loss": 3.4764,
"step": 1597952
},
{
"epoch": 1.02,
"learning_rate": 2.3830422383142152e-05,
"loss": 3.4643,
"step": 1598464
},
{
"epoch": 1.02,
"learning_rate": 2.3822036435631632e-05,
"loss": 3.4718,
"step": 1598976
},
{
"epoch": 1.02,
"learning_rate": 2.381366686692484e-05,
"loss": 3.4682,
"step": 1599488
},
{
"epoch": 1.02,
"learning_rate": 2.380528091941432e-05,
"loss": 3.4624,
"step": 1600000
},
{
"epoch": 1.02,
"learning_rate": 2.37968949719038e-05,
"loss": 3.469,
"step": 1600512
},
{
"epoch": 1.02,
"learning_rate": 2.378850902439328e-05,
"loss": 3.4783,
"step": 1601024
},
{
"epoch": 1.02,
"learning_rate": 2.3780139455686493e-05,
"loss": 3.4705,
"step": 1601536
},
{
"epoch": 1.02,
"learning_rate": 2.3771753508175973e-05,
"loss": 3.4579,
"step": 1602048
},
{
"epoch": 1.02,
"learning_rate": 2.3763367560665453e-05,
"loss": 3.4654,
"step": 1602560
},
{
"epoch": 1.03,
"eval_loss": 3.8540024757385254,
"eval_runtime": 310.3511,
"eval_samples_per_second": 1229.546,
"eval_steps_per_second": 38.424,
"step": 1602720
},
{
"epoch": 0.0,
"learning_rate": 2.3754981613154933e-05,
"loss": 3.4679,
"step": 1603072
},
{
"epoch": 0.0,
"learning_rate": 2.374659566564441e-05,
"loss": 3.4605,
"step": 1603584
},
{
"epoch": 0.0,
"learning_rate": 2.3738209718133893e-05,
"loss": 3.4654,
"step": 1604096
},
{
"epoch": 0.0,
"learning_rate": 2.3729823770623373e-05,
"loss": 3.4727,
"step": 1604608
},
{
"epoch": 0.0,
"learning_rate": 2.3721454201916582e-05,
"loss": 3.4794,
"step": 1605120
},
{
"epoch": 0.0,
"learning_rate": 2.3713068254406062e-05,
"loss": 3.4653,
"step": 1605632
},
{
"epoch": 0.0,
"learning_rate": 2.3704682306895542e-05,
"loss": 3.4594,
"step": 1606144
},
{
"epoch": 0.0,
"learning_rate": 2.3696296359385022e-05,
"loss": 3.4545,
"step": 1606656
},
{
"epoch": 0.0,
"learning_rate": 2.3687926790678234e-05,
"loss": 3.4681,
"step": 1607168
},
{
"epoch": 0.0,
"learning_rate": 2.3679540843167714e-05,
"loss": 3.4721,
"step": 1607680
},
{
"epoch": 0.0,
"learning_rate": 2.3671154895657194e-05,
"loss": 3.4632,
"step": 1608192
},
{
"epoch": 0.0,
"learning_rate": 2.3662768948146674e-05,
"loss": 3.4685,
"step": 1608704
},
{
"epoch": 0.0,
"learning_rate": 2.3654399379439883e-05,
"loss": 3.4582,
"step": 1609216
},
{
"epoch": 0.0,
"learning_rate": 2.3646013431929363e-05,
"loss": 3.4652,
"step": 1609728
},
{
"epoch": 0.0,
"learning_rate": 2.3637627484418847e-05,
"loss": 3.4547,
"step": 1610240
},
{
"epoch": 0.0,
"learning_rate": 2.3629241536908327e-05,
"loss": 3.4633,
"step": 1610752
},
{
"epoch": 0.0,
"learning_rate": 2.3620871968201536e-05,
"loss": 3.456,
"step": 1611264
},
{
"epoch": 0.0,
"learning_rate": 2.3612486020691016e-05,
"loss": 3.464,
"step": 1611776
},
{
"epoch": 0.0,
"learning_rate": 2.3604100073180496e-05,
"loss": 3.4604,
"step": 1612288
},
{
"epoch": 0.0,
"learning_rate": 2.3595714125669976e-05,
"loss": 3.4772,
"step": 1612800
},
{
"epoch": 0.0,
"learning_rate": 2.3587344556963188e-05,
"loss": 3.4653,
"step": 1613312
},
{
"epoch": 0.0,
"learning_rate": 2.3578958609452668e-05,
"loss": 3.4733,
"step": 1613824
},
{
"epoch": 0.0,
"learning_rate": 2.3570572661942148e-05,
"loss": 3.4612,
"step": 1614336
},
{
"epoch": 0.0,
"learning_rate": 2.3562186714431628e-05,
"loss": 3.4694,
"step": 1614848
},
{
"epoch": 0.0,
"learning_rate": 2.3553817145724837e-05,
"loss": 3.4576,
"step": 1615360
},
{
"epoch": 0.0,
"learning_rate": 2.3545431198214317e-05,
"loss": 3.4694,
"step": 1615872
},
{
"epoch": 0.0,
"learning_rate": 2.35370452507038e-05,
"loss": 3.466,
"step": 1616384
},
{
"epoch": 0.0,
"learning_rate": 2.352865930319328e-05,
"loss": 3.4539,
"step": 1616896
},
{
"epoch": 0.0,
"learning_rate": 2.352028973448649e-05,
"loss": 3.4502,
"step": 1617408
},
{
"epoch": 0.0,
"learning_rate": 2.351190378697597e-05,
"loss": 3.4564,
"step": 1617920
},
{
"epoch": 0.01,
"learning_rate": 2.350351783946545e-05,
"loss": 3.4626,
"step": 1618432
},
{
"epoch": 0.01,
"learning_rate": 2.349513189195493e-05,
"loss": 3.4658,
"step": 1618944
},
{
"epoch": 0.01,
"learning_rate": 2.348676232324814e-05,
"loss": 3.471,
"step": 1619456
},
{
"epoch": 0.01,
"learning_rate": 2.347837637573762e-05,
"loss": 3.4705,
"step": 1619968
},
{
"epoch": 0.01,
"learning_rate": 2.34699904282271e-05,
"loss": 3.458,
"step": 1620480
},
{
"epoch": 0.01,
"learning_rate": 2.346160448071658e-05,
"loss": 3.4684,
"step": 1620992
},
{
"epoch": 0.01,
"learning_rate": 2.345323491200979e-05,
"loss": 3.4621,
"step": 1621504
},
{
"epoch": 0.01,
"learning_rate": 2.344484896449927e-05,
"loss": 3.4617,
"step": 1622016
},
{
"epoch": 0.01,
"learning_rate": 2.3436463016988754e-05,
"loss": 3.4464,
"step": 1622528
},
{
"epoch": 0.01,
"learning_rate": 2.3428077069478234e-05,
"loss": 3.4621,
"step": 1623040
},
{
"epoch": 0.01,
"learning_rate": 2.3419707500771443e-05,
"loss": 3.4569,
"step": 1623552
},
{
"epoch": 0.01,
"learning_rate": 2.3411321553260923e-05,
"loss": 3.4702,
"step": 1624064
},
{
"epoch": 0.01,
"learning_rate": 2.3402935605750403e-05,
"loss": 3.4625,
"step": 1624576
},
{
"epoch": 0.01,
"learning_rate": 2.3394549658239883e-05,
"loss": 3.4552,
"step": 1625088
},
{
"epoch": 0.01,
"learning_rate": 2.3386180089533095e-05,
"loss": 3.4712,
"step": 1625600
},
{
"epoch": 0.01,
"learning_rate": 2.3377794142022575e-05,
"loss": 3.457,
"step": 1626112
},
{
"epoch": 0.01,
"learning_rate": 2.3369408194512055e-05,
"loss": 3.4566,
"step": 1626624
},
{
"epoch": 0.01,
"learning_rate": 2.3361022247001532e-05,
"loss": 3.4517,
"step": 1627136
},
{
"epoch": 0.01,
"learning_rate": 2.3352652678294744e-05,
"loss": 3.4485,
"step": 1627648
},
{
"epoch": 0.01,
"learning_rate": 2.3344266730784224e-05,
"loss": 3.4636,
"step": 1628160
},
{
"epoch": 0.01,
"learning_rate": 2.3335880783273704e-05,
"loss": 3.4626,
"step": 1628672
},
{
"epoch": 0.01,
"learning_rate": 2.3327494835763184e-05,
"loss": 3.455,
"step": 1629184
},
{
"epoch": 0.01,
"learning_rate": 2.3319125267056397e-05,
"loss": 3.4513,
"step": 1629696
},
{
"epoch": 0.01,
"learning_rate": 2.3310739319545877e-05,
"loss": 3.462,
"step": 1630208
},
{
"epoch": 0.01,
"learning_rate": 2.3302353372035357e-05,
"loss": 3.4427,
"step": 1630720
},
{
"epoch": 0.01,
"learning_rate": 2.3293967424524833e-05,
"loss": 3.4655,
"step": 1631232
},
{
"epoch": 0.01,
"learning_rate": 2.328559785581805e-05,
"loss": 3.4557,
"step": 1631744
},
{
"epoch": 0.01,
"learning_rate": 2.327721190830753e-05,
"loss": 3.4603,
"step": 1632256
},
{
"epoch": 0.01,
"learning_rate": 2.3268825960797006e-05,
"loss": 3.4583,
"step": 1632768
},
{
"epoch": 0.01,
"learning_rate": 2.3260440013286485e-05,
"loss": 3.457,
"step": 1633280
},
{
"epoch": 0.01,
"learning_rate": 2.3252070444579698e-05,
"loss": 3.4504,
"step": 1633792
},
{
"epoch": 0.01,
"learning_rate": 2.3243684497069178e-05,
"loss": 3.4607,
"step": 1634304
},
{
"epoch": 0.01,
"learning_rate": 2.3235298549558658e-05,
"loss": 3.454,
"step": 1634816
},
{
"epoch": 0.01,
"learning_rate": 2.3226912602048138e-05,
"loss": 3.4522,
"step": 1635328
},
{
"epoch": 0.01,
"learning_rate": 2.321854303334135e-05,
"loss": 3.4608,
"step": 1635840
},
{
"epoch": 0.01,
"learning_rate": 2.321015708583083e-05,
"loss": 3.461,
"step": 1636352
},
{
"epoch": 0.01,
"learning_rate": 2.3201771138320307e-05,
"loss": 3.4464,
"step": 1636864
},
{
"epoch": 0.01,
"learning_rate": 2.3193385190809787e-05,
"loss": 3.4568,
"step": 1637376
},
{
"epoch": 0.01,
"learning_rate": 2.3185015622103003e-05,
"loss": 3.4477,
"step": 1637888
},
{
"epoch": 0.01,
"learning_rate": 2.317662967459248e-05,
"loss": 3.4508,
"step": 1638400
},
{
"epoch": 0.01,
"learning_rate": 2.316824372708196e-05,
"loss": 3.4664,
"step": 1638912
},
{
"epoch": 0.01,
"learning_rate": 2.315985777957144e-05,
"loss": 3.4602,
"step": 1639424
},
{
"epoch": 0.01,
"learning_rate": 2.315148821086465e-05,
"loss": 3.4649,
"step": 1639936
},
{
"epoch": 0.01,
"learning_rate": 2.314310226335413e-05,
"loss": 3.463,
"step": 1640448
},
{
"epoch": 0.01,
"learning_rate": 2.313471631584361e-05,
"loss": 3.4742,
"step": 1640960
},
{
"epoch": 0.01,
"learning_rate": 2.312633036833309e-05,
"loss": 3.4545,
"step": 1641472
},
{
"epoch": 0.01,
"learning_rate": 2.3117960799626304e-05,
"loss": 3.4569,
"step": 1641984
},
{
"epoch": 0.01,
"learning_rate": 2.310957485211578e-05,
"loss": 3.4674,
"step": 1642496
},
{
"epoch": 0.01,
"learning_rate": 2.310118890460526e-05,
"loss": 3.4546,
"step": 1643008
},
{
"epoch": 0.01,
"learning_rate": 2.3092819335898473e-05,
"loss": 3.4632,
"step": 1643520
},
{
"epoch": 0.01,
"learning_rate": 2.3084433388387953e-05,
"loss": 3.464,
"step": 1644032
},
{
"epoch": 0.01,
"learning_rate": 2.3076047440877433e-05,
"loss": 3.4678,
"step": 1644544
},
{
"epoch": 0.01,
"learning_rate": 2.3067661493366913e-05,
"loss": 3.4588,
"step": 1645056
},
{
"epoch": 0.01,
"learning_rate": 2.3059275545856393e-05,
"loss": 3.4459,
"step": 1645568
},
{
"epoch": 0.01,
"learning_rate": 2.3050889598345873e-05,
"loss": 3.4517,
"step": 1646080
},
{
"epoch": 0.01,
"learning_rate": 2.3042503650835353e-05,
"loss": 3.4572,
"step": 1646592
},
{
"epoch": 0.01,
"learning_rate": 2.3034117703324833e-05,
"loss": 3.4645,
"step": 1647104
},
{
"epoch": 0.01,
"learning_rate": 2.3025748134618045e-05,
"loss": 3.4645,
"step": 1647616
},
{
"epoch": 0.01,
"learning_rate": 2.3017362187107525e-05,
"loss": 3.4581,
"step": 1648128
},
{
"epoch": 0.02,
"learning_rate": 2.3008976239597005e-05,
"loss": 3.462,
"step": 1648640
},
{
"epoch": 0.02,
"learning_rate": 2.3000590292086485e-05,
"loss": 3.4495,
"step": 1649152
},
{
"epoch": 0.02,
"learning_rate": 2.2992220723379694e-05,
"loss": 3.4503,
"step": 1649664
},
{
"epoch": 0.02,
"learning_rate": 2.2983834775869174e-05,
"loss": 3.4565,
"step": 1650176
},
{
"epoch": 0.02,
"learning_rate": 2.2975448828358657e-05,
"loss": 3.4664,
"step": 1650688
},
{
"epoch": 0.02,
"learning_rate": 2.2967062880848134e-05,
"loss": 3.4791,
"step": 1651200
},
{
"epoch": 0.02,
"learning_rate": 2.2958693312141346e-05,
"loss": 3.4688,
"step": 1651712
},
{
"epoch": 0.02,
"learning_rate": 2.2950307364630826e-05,
"loss": 3.4447,
"step": 1652224
},
{
"epoch": 0.02,
"learning_rate": 2.2941921417120306e-05,
"loss": 3.4644,
"step": 1652736
},
{
"epoch": 0.02,
"learning_rate": 2.2933535469609786e-05,
"loss": 3.4527,
"step": 1653248
},
{
"epoch": 0.02,
"learning_rate": 2.2925165900903e-05,
"loss": 3.4661,
"step": 1653760
},
{
"epoch": 0.02,
"learning_rate": 2.291677995339248e-05,
"loss": 3.4569,
"step": 1654272
},
{
"epoch": 0.02,
"learning_rate": 2.2908394005881955e-05,
"loss": 3.4567,
"step": 1654784
},
{
"epoch": 0.02,
"learning_rate": 2.2900008058371435e-05,
"loss": 3.4585,
"step": 1655296
},
{
"epoch": 0.02,
"learning_rate": 2.2891638489664648e-05,
"loss": 3.4615,
"step": 1655808
},
{
"epoch": 0.02,
"learning_rate": 2.2883252542154128e-05,
"loss": 3.4518,
"step": 1656320
},
{
"epoch": 0.02,
"learning_rate": 2.2874866594643608e-05,
"loss": 3.4561,
"step": 1656832
},
{
"epoch": 0.02,
"learning_rate": 2.2866480647133088e-05,
"loss": 3.4457,
"step": 1657344
},
{
"epoch": 0.02,
"learning_rate": 2.28581110784263e-05,
"loss": 3.4692,
"step": 1657856
},
{
"epoch": 0.02,
"learning_rate": 2.284972513091578e-05,
"loss": 3.4529,
"step": 1658368
},
{
"epoch": 0.02,
"learning_rate": 2.2841339183405257e-05,
"loss": 3.4536,
"step": 1658880
},
{
"epoch": 0.02,
"learning_rate": 2.283295323589474e-05,
"loss": 3.4473,
"step": 1659392
},
{
"epoch": 0.02,
"learning_rate": 2.2824583667187952e-05,
"loss": 3.4598,
"step": 1659904
},
{
"epoch": 0.02,
"learning_rate": 2.281619771967743e-05,
"loss": 3.4575,
"step": 1660416
},
{
"epoch": 0.02,
"learning_rate": 2.280781177216691e-05,
"loss": 3.4575,
"step": 1660928
},
{
"epoch": 0.02,
"learning_rate": 2.279942582465639e-05,
"loss": 3.4644,
"step": 1661440
},
{
"epoch": 0.02,
"learning_rate": 2.27910562559496e-05,
"loss": 3.467,
"step": 1661952
},
{
"epoch": 0.02,
"learning_rate": 2.278267030843908e-05,
"loss": 3.46,
"step": 1662464
},
{
"epoch": 0.02,
"learning_rate": 2.277428436092856e-05,
"loss": 3.4551,
"step": 1662976
},
{
"epoch": 0.02,
"learning_rate": 2.276589841341804e-05,
"loss": 3.4524,
"step": 1663488
},
{
"epoch": 0.02,
"learning_rate": 2.2757528844711254e-05,
"loss": 3.4662,
"step": 1664000
},
{
"epoch": 0.02,
"learning_rate": 2.274914289720073e-05,
"loss": 3.4485,
"step": 1664512
},
{
"epoch": 0.02,
"learning_rate": 2.274075694969021e-05,
"loss": 3.4588,
"step": 1665024
},
{
"epoch": 0.02,
"learning_rate": 2.2732371002179694e-05,
"loss": 3.4491,
"step": 1665536
},
{
"epoch": 0.02,
"learning_rate": 2.2724001433472903e-05,
"loss": 3.4623,
"step": 1666048
},
{
"epoch": 0.02,
"learning_rate": 2.2715615485962383e-05,
"loss": 3.4474,
"step": 1666560
},
{
"epoch": 0.02,
"learning_rate": 2.2707229538451863e-05,
"loss": 3.4549,
"step": 1667072
},
{
"epoch": 0.02,
"learning_rate": 2.2698843590941343e-05,
"loss": 3.4538,
"step": 1667584
},
{
"epoch": 0.02,
"learning_rate": 2.2690474022234555e-05,
"loss": 3.4542,
"step": 1668096
},
{
"epoch": 0.02,
"learning_rate": 2.2682088074724035e-05,
"loss": 3.4535,
"step": 1668608
},
{
"epoch": 0.02,
"learning_rate": 2.2673702127213515e-05,
"loss": 3.4641,
"step": 1669120
},
{
"epoch": 0.02,
"learning_rate": 2.2665316179702995e-05,
"loss": 3.4664,
"step": 1669632
},
{
"epoch": 0.02,
"learning_rate": 2.2656946610996204e-05,
"loss": 3.4685,
"step": 1670144
},
{
"epoch": 0.02,
"learning_rate": 2.2648560663485684e-05,
"loss": 3.4429,
"step": 1670656
},
{
"epoch": 0.02,
"learning_rate": 2.2640174715975164e-05,
"loss": 3.4629,
"step": 1671168
},
{
"epoch": 0.02,
"learning_rate": 2.2631788768464647e-05,
"loss": 3.461,
"step": 1671680
},
{
"epoch": 0.02,
"learning_rate": 2.2623419199757856e-05,
"loss": 3.4618,
"step": 1672192
},
{
"epoch": 0.02,
"learning_rate": 2.2615033252247336e-05,
"loss": 3.4571,
"step": 1672704
},
{
"epoch": 0.02,
"learning_rate": 2.2606647304736816e-05,
"loss": 3.4627,
"step": 1673216
},
{
"epoch": 0.02,
"learning_rate": 2.2598261357226296e-05,
"loss": 3.4558,
"step": 1673728
},
{
"epoch": 0.02,
"learning_rate": 2.258989178851951e-05,
"loss": 3.4705,
"step": 1674240
},
{
"epoch": 0.02,
"learning_rate": 2.258150584100899e-05,
"loss": 3.451,
"step": 1674752
},
{
"epoch": 0.02,
"learning_rate": 2.257311989349847e-05,
"loss": 3.4607,
"step": 1675264
},
{
"epoch": 0.02,
"learning_rate": 2.2564750324791678e-05,
"loss": 3.454,
"step": 1675776
},
{
"epoch": 0.02,
"learning_rate": 2.2556364377281158e-05,
"loss": 3.454,
"step": 1676288
},
{
"epoch": 0.02,
"learning_rate": 2.2547978429770638e-05,
"loss": 3.4598,
"step": 1676800
},
{
"epoch": 0.02,
"learning_rate": 2.2539592482260118e-05,
"loss": 3.4602,
"step": 1677312
},
{
"epoch": 0.02,
"learning_rate": 2.253122291355333e-05,
"loss": 3.4636,
"step": 1677824
},
{
"epoch": 0.02,
"learning_rate": 2.252283696604281e-05,
"loss": 3.4431,
"step": 1678336
},
{
"epoch": 0.02,
"learning_rate": 2.251445101853229e-05,
"loss": 3.455,
"step": 1678848
},
{
"epoch": 0.03,
"eval_loss": 3.855130672454834,
"eval_runtime": 321.3211,
"eval_samples_per_second": 1187.569,
"eval_steps_per_second": 37.112,
"step": 1679040
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.1708460903967027e+18,
"trial_name": null,
"trial_params": null
}