abhinavp's picture
Training in progress, epoch 0, checkpoint
a9016a8 verified
{
"best_metric": 3.8472540378570557,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/1/checkpoints/checkpoint-839510",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 839510,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9662,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8384,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2003,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.984,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8361,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7163,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6151,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.549,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4911,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4148,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3799,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3402,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2804,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2292,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.2031,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1705,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 5.1368,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0909,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0723,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0415,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0156,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9989,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9769,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9514,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9293,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.9153,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.89,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8802,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8445,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8481,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8142,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.8057,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.8064,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7902,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7639,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7501,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7525,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7349,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.7245,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.7072,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 4.6911,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 4.68,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6665,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.667,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6573,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 4.6531,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 4.637,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6343,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6367,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 4.6138,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 4.6078,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5968,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.6061,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 4.5712,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 4.5898,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5639,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5614,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5622,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5535,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 4.5372,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5301,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5188,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5324,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.517,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5067,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5061,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4966,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4777,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.499,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4775,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4723,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4834,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4639,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4763,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.473,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4608,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4655,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4382,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4353,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4392,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4381,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.432,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4173,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4089,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4109,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.4117,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.411,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.4136,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.4098,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 4.3971,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3838,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3817,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3886,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3844,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3662,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 4.3722,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 4.3718,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3761,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3706,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3653,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3666,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3564,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3536,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.3621,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3462,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3513,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.332,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.328,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.3271,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.3365,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3306,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3082,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3125,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.3217,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.3302,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.313,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3194,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.3112,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.3137,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.3042,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.3001,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.2937,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.3029,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968872411084396e-05,
"loss": 4.2869,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.295,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.2879,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.2975,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.2724,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.2844,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.2936,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.2718,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2909,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2763,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2771,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.271,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.263,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2664,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2703,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2761,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2647,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2683,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2612,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2484,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2555,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.2427,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2467,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2466,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2414,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.239,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.238,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.202739715576172,
"eval_runtime": 573.4896,
"eval_samples_per_second": 665.384,
"eval_steps_per_second": 20.794,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2444,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2388,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2311,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2298,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2306,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.2059,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.2215,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.2212,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.8675478899842306e-05,
"loss": 4.2108,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.8667092952331785e-05,
"loss": 4.2213,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.865870700482127e-05,
"loss": 4.2224,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865032105731075e-05,
"loss": 4.2059,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.8641935109800225e-05,
"loss": 4.2052,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.8633549162289705e-05,
"loss": 4.2054,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.8625163214779185e-05,
"loss": 4.2053,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.86167936460724e-05,
"loss": 4.1927,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.8608407698561874e-05,
"loss": 4.1961,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.8600021751051354e-05,
"loss": 4.1975,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.8591635803540834e-05,
"loss": 4.194,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.8583249856030314e-05,
"loss": 4.1983,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.8574863908519794e-05,
"loss": 4.1962,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.8566477961009274e-05,
"loss": 4.1978,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.1915,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.854972244479197e-05,
"loss": 4.1898,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.854133649728145e-05,
"loss": 4.1876,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.853295054977093e-05,
"loss": 4.184,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.852456460226041e-05,
"loss": 4.1904,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.851617865474989e-05,
"loss": 4.1699,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.85078090860431e-05,
"loss": 4.1829,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.849942313853258e-05,
"loss": 4.1675,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.849103719102206e-05,
"loss": 4.1732,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.848265124351154e-05,
"loss": 4.1822,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847426529600102e-05,
"loss": 4.1788,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.1677,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845750977978371e-05,
"loss": 4.1617,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.8449123832273194e-05,
"loss": 4.1753,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.8440737884762674e-05,
"loss": 4.1658,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.8432368316055884e-05,
"loss": 4.1661,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.8423982368545363e-05,
"loss": 4.1607,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.8415596421034843e-05,
"loss": 4.1479,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840721047352432e-05,
"loss": 4.1464,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.83988245260138e-05,
"loss": 4.1464,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839043857850328e-05,
"loss": 4.1559,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.838206900979649e-05,
"loss": 4.1457,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.837368306228597e-05,
"loss": 4.1492,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836529711477545e-05,
"loss": 4.1462,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.835691116726493e-05,
"loss": 4.1477,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834852521975441e-05,
"loss": 4.1575,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834013927224389e-05,
"loss": 4.1374,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833176970353711e-05,
"loss": 4.1404,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832338375602659e-05,
"loss": 4.1316,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.831499780851606e-05,
"loss": 4.1546,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.830661186100554e-05,
"loss": 4.1243,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.829824229229876e-05,
"loss": 4.142,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.828985634478824e-05,
"loss": 4.1252,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.828147039727771e-05,
"loss": 4.1316,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.827308444976719e-05,
"loss": 4.1332,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.826469850225667e-05,
"loss": 4.1308,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.8256328933549886e-05,
"loss": 4.1197,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8247942986039366e-05,
"loss": 4.1241,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.8239557038528846e-05,
"loss": 4.1099,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.8231171091018326e-05,
"loss": 4.1266,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.1223,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.1161,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.8206029627290495e-05,
"loss": 4.1143,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.8197643679779975e-05,
"loss": 4.1158,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.8189257732269455e-05,
"loss": 4.097,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.121,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.1049,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.1074,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.8155730321031104e-05,
"loss": 4.1163,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.1034,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.1161,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.1203,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812220290979276e-05,
"loss": 4.1136,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.1171,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.0976,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.0919,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808867549855441e-05,
"loss": 4.1001,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.1079,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.0998,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.0916,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.0819,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.804676213980554e-05,
"loss": 4.0857,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.0879,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.091,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.1018,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.0975,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.0874,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.0827,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.0765,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.0835,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.0838,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.0765,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.0755,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.0813,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.0877,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.0814,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.0801,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.0857,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.0773,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.0733,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.0864,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.7879141462417525e-05,
"loss": 4.0715,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870755514907005e-05,
"loss": 4.0832,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862369567396485e-05,
"loss": 4.067,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.0565,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.0647,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.0715,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.0653,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.0544,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.0502,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.0637,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.073,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.061,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.0729,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.0602,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.0618,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.0609,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.0534,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.0502,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.0615,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.0488,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.0523,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.0516,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.0635,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.0408,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.767794423737997e-05,
"loss": 4.0455,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.0643,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.0427,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.0616,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.7644416826141616e-05,
"loss": 4.046,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.0535,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.0437,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.039,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761088941490327e-05,
"loss": 4.0437,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760250346739275e-05,
"loss": 4.0485,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759411751988223e-05,
"loss": 4.0583,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.758573157237171e-05,
"loss": 4.0512,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757736200366492e-05,
"loss": 4.0492,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.0439,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756059010864388e-05,
"loss": 4.0309,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755220416113336e-05,
"loss": 4.0428,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.754383459242657e-05,
"loss": 4.0314,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.7535465023719786e-05,
"loss": 4.0343,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.7527079076209266e-05,
"loss": 4.0394,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.7518693128698745e-05,
"loss": 4.0269,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.7510307181188225e-05,
"loss": 4.0353,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.0312,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.032494068145752,
"eval_runtime": 578.1785,
"eval_samples_per_second": 659.988,
"eval_steps_per_second": 20.625,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.7493551664970914e-05,
"loss": 4.0392,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485165717460394e-05,
"loss": 4.0357,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476779769949874e-05,
"loss": 4.0304,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468393822439354e-05,
"loss": 4.0282,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460007874928834e-05,
"loss": 4.0321,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451621927418314e-05,
"loss": 4.0123,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443235979907794e-05,
"loss": 4.0277,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434850032397274e-05,
"loss": 4.0227,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426464084886754e-05,
"loss": 4.0134,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741809451617997e-05,
"loss": 4.0263,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740970856866945e-05,
"loss": 4.0318,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740132262115893e-05,
"loss": 4.015,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739293667364841e-05,
"loss": 4.0122,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738455072613789e-05,
"loss": 4.0157,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737616477862737e-05,
"loss": 4.0181,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736777883111685e-05,
"loss": 4.0077,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735939288360632e-05,
"loss": 4.0093,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735102331489954e-05,
"loss": 4.0118,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734263736738902e-05,
"loss": 4.014,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.73342514198785e-05,
"loss": 4.0152,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732586547236797e-05,
"loss": 4.0131,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731749590366119e-05,
"loss": 4.0191,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309109956150674e-05,
"loss": 4.0139,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300724008640154e-05,
"loss": 4.0072,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729233806112963e-05,
"loss": 4.0109,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283968492422844e-05,
"loss": 4.0092,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275582544912323e-05,
"loss": 4.0132,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.72671965974018e-05,
"loss": 3.9971,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725882702869501e-05,
"loss": 4.0074,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725044108118449e-05,
"loss": 3.996,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724205513367397e-05,
"loss": 4.0018,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233669186163446e-05,
"loss": 4.0126,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225283238652926e-05,
"loss": 4.0083,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721689729114241e-05,
"loss": 4.0004,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720851134363189e-05,
"loss": 3.9945,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.72001417749251e-05,
"loss": 4.0107,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719175582741458e-05,
"loss": 3.9949,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718336987990406e-05,
"loss": 4.0012,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717498393239354e-05,
"loss": 3.9959,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716659798488302e-05,
"loss": 3.9813,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.71582120373725e-05,
"loss": 3.9833,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714982608986198e-05,
"loss": 3.9804,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714144014235146e-05,
"loss": 3.9994,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713307057364467e-05,
"loss": 3.9874,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712468462613415e-05,
"loss": 3.9885,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711629867862363e-05,
"loss": 3.9852,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710791273111311e-05,
"loss": 3.9858,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099543162406326e-05,
"loss": 4.0007,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091157214895806e-05,
"loss": 3.9807,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082771267385286e-05,
"loss": 3.9798,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074385319874766e-05,
"loss": 3.9783,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7066015751167975e-05,
"loss": 3.9996,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057629803657455e-05,
"loss": 3.9722,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049243856146935e-05,
"loss": 3.9878,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040857908636415e-05,
"loss": 3.9686,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032488339929624e-05,
"loss": 3.9832,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702411877122283e-05,
"loss": 3.9849,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701573282371232e-05,
"loss": 3.9746,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70073468762018e-05,
"loss": 3.9794,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699896092869128e-05,
"loss": 3.9774,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699057498118076e-05,
"loss": 3.9566,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698218903367024e-05,
"loss": 3.9758,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697381946496345e-05,
"loss": 3.979,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696543351745293e-05,
"loss": 3.9712,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695704756994241e-05,
"loss": 3.9683,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694866162243189e-05,
"loss": 3.9718,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694027567492137e-05,
"loss": 3.956,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693188972741085e-05,
"loss": 3.9783,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692350377990033e-05,
"loss": 3.9575,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691511783238981e-05,
"loss": 3.9659,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690674826368302e-05,
"loss": 3.9741,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.68983623161725e-05,
"loss": 3.9628,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6889976368661984e-05,
"loss": 3.9724,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688159042115146e-05,
"loss": 3.9833,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687322085244467e-05,
"loss": 3.9698,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686483490493415e-05,
"loss": 3.9803,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685644895742363e-05,
"loss": 3.9612,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848063009913106e-05,
"loss": 3.9519,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683969344120632e-05,
"loss": 3.9628,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.68313074936958e-05,
"loss": 3.9744,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682292154618528e-05,
"loss": 3.9625,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814535598674755e-05,
"loss": 3.9531,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680616602996797e-05,
"loss": 3.949,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679778008245745e-05,
"loss": 3.9523,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678939413494693e-05,
"loss": 3.9512,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678102456624015e-05,
"loss": 3.9569,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677263861872963e-05,
"loss": 3.9662,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676425267121911e-05,
"loss": 3.9644,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675586672370858e-05,
"loss": 3.9562,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674748077619806e-05,
"loss": 3.9521,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673909482868754e-05,
"loss": 3.9452,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673070888117702e-05,
"loss": 3.954,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672233931247023e-05,
"loss": 3.9498,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671395336495971e-05,
"loss": 3.9514,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670556741744919e-05,
"loss": 3.9462,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697181469938675e-05,
"loss": 3.9556,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688795522428155e-05,
"loss": 3.9553,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680409574917635e-05,
"loss": 3.9559,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672023627407115e-05,
"loss": 3.9546,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663637679896595e-05,
"loss": 3.9569,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655268111189804e-05,
"loss": 3.9512,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646898542483013e-05,
"loss": 3.9462,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638512594972493e-05,
"loss": 3.9636,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.6630126647461973e-05,
"loss": 3.9421,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662174069995145e-05,
"loss": 3.9638,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661335475244093e-05,
"loss": 3.9378,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660496880493041e-05,
"loss": 3.935,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659658285741989e-05,
"loss": 3.9403,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658819690990937e-05,
"loss": 3.9524,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657982734120259e-05,
"loss": 3.9441,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657144139369207e-05,
"loss": 3.9309,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656305544618155e-05,
"loss": 3.9299,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655466949867103e-05,
"loss": 3.94,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654628355116051e-05,
"loss": 3.9532,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653791398245372e-05,
"loss": 3.9388,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.65295280349432e-05,
"loss": 3.9527,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652114208743268e-05,
"loss": 3.9397,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651275613992216e-05,
"loss": 3.9421,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650438657121537e-05,
"loss": 3.9473,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649600062370485e-05,
"loss": 3.9325,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648761467619433e-05,
"loss": 3.9349,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647922872868381e-05,
"loss": 3.9412,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470842781173294e-05,
"loss": 3.932,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646245683366277e-05,
"loss": 3.9365,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645407088615225e-05,
"loss": 3.9363,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644568493864173e-05,
"loss": 3.9442,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643731536993494e-05,
"loss": 3.9275,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642894580122815e-05,
"loss": 3.9262,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642055985371763e-05,
"loss": 3.9516,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641217390620711e-05,
"loss": 3.9302,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640378795869659e-05,
"loss": 3.9444,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395402011186065e-05,
"loss": 3.9349,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387016063675545e-05,
"loss": 3.9392,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637864649496876e-05,
"loss": 3.9306,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637026054745824e-05,
"loss": 3.9261,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636187459994772e-05,
"loss": 3.9348,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.63534886524372e-05,
"loss": 3.9347,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634510270492668e-05,
"loss": 3.9459,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633671675741616e-05,
"loss": 3.9412,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632834718870937e-05,
"loss": 3.937,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631996124119885e-05,
"loss": 3.9321,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631157529368833e-05,
"loss": 3.9226,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630318934617781e-05,
"loss": 3.9317,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629480339866729e-05,
"loss": 3.9221,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864338299605e-05,
"loss": 3.9265,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278047882449985e-05,
"loss": 3.9278,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269661934939465e-05,
"loss": 3.9194,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261275987428945e-05,
"loss": 3.9265,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252890039918425e-05,
"loss": 3.9229,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9574086666107178,
"eval_runtime": 564.865,
"eval_samples_per_second": 675.544,
"eval_steps_per_second": 21.111,
"step": 228957
},
{
"epoch": 0.0,
"learning_rate": 4.6244520471211634e-05,
"loss": 3.9292,
"step": 229376
},
{
"epoch": 0.0,
"learning_rate": 4.6236134523701114e-05,
"loss": 3.932,
"step": 229888
},
{
"epoch": 0.0,
"learning_rate": 4.6227748576190594e-05,
"loss": 3.922,
"step": 230400
},
{
"epoch": 0.0,
"learning_rate": 4.6219362628680074e-05,
"loss": 3.9237,
"step": 230912
},
{
"epoch": 0.0,
"learning_rate": 4.6210976681169554e-05,
"loss": 3.926,
"step": 231424
},
{
"epoch": 0.0,
"learning_rate": 4.6202590733659034e-05,
"loss": 3.9066,
"step": 231936
},
{
"epoch": 0.0,
"learning_rate": 4.6194204786148514e-05,
"loss": 3.9215,
"step": 232448
},
{
"epoch": 0.0,
"learning_rate": 4.6185818838637994e-05,
"loss": 3.9211,
"step": 232960
},
{
"epoch": 0.0,
"learning_rate": 4.6177432891127474e-05,
"loss": 3.91,
"step": 233472
},
{
"epoch": 0.0,
"learning_rate": 4.616906332242068e-05,
"loss": 3.9218,
"step": 233984
},
{
"epoch": 0.0,
"learning_rate": 4.616067737491017e-05,
"loss": 3.9265,
"step": 234496
},
{
"epoch": 0.0,
"learning_rate": 4.615229142739965e-05,
"loss": 3.907,
"step": 235008
},
{
"epoch": 0.0,
"learning_rate": 4.614390547988913e-05,
"loss": 3.9101,
"step": 235520
},
{
"epoch": 0.0,
"learning_rate": 4.613553591118234e-05,
"loss": 3.9142,
"step": 236032
},
{
"epoch": 0.0,
"learning_rate": 4.612714996367182e-05,
"loss": 3.9161,
"step": 236544
},
{
"epoch": 0.0,
"learning_rate": 4.61187640161613e-05,
"loss": 3.9033,
"step": 237056
},
{
"epoch": 0.0,
"learning_rate": 4.611037806865078e-05,
"loss": 3.9057,
"step": 237568
},
{
"epoch": 0.0,
"learning_rate": 4.610199212114025e-05,
"loss": 3.9098,
"step": 238080
},
{
"epoch": 0.0,
"learning_rate": 4.609362255243347e-05,
"loss": 3.9105,
"step": 238592
},
{
"epoch": 0.0,
"learning_rate": 4.608523660492295e-05,
"loss": 3.9163,
"step": 239104
},
{
"epoch": 0.0,
"learning_rate": 4.607685065741242e-05,
"loss": 3.9086,
"step": 239616
},
{
"epoch": 0.0,
"learning_rate": 4.606846470990191e-05,
"loss": 3.9217,
"step": 240128
},
{
"epoch": 0.0,
"learning_rate": 4.606007876239139e-05,
"loss": 3.915,
"step": 240640
},
{
"epoch": 0.0,
"learning_rate": 4.60517091936846e-05,
"loss": 3.9098,
"step": 241152
},
{
"epoch": 0.0,
"learning_rate": 4.6043323246174076e-05,
"loss": 3.9087,
"step": 241664
},
{
"epoch": 0.0,
"learning_rate": 4.6034937298663556e-05,
"loss": 3.9087,
"step": 242176
},
{
"epoch": 0.0,
"learning_rate": 4.6026551351153036e-05,
"loss": 3.9156,
"step": 242688
},
{
"epoch": 0.0,
"learning_rate": 4.6018165403642516e-05,
"loss": 3.9022,
"step": 243200
},
{
"epoch": 0.0,
"learning_rate": 4.6009795834935725e-05,
"loss": 3.9102,
"step": 243712
},
{
"epoch": 0.01,
"learning_rate": 4.6001409887425205e-05,
"loss": 3.8993,
"step": 244224
},
{
"epoch": 0.01,
"learning_rate": 4.5993023939914685e-05,
"loss": 3.901,
"step": 244736
},
{
"epoch": 0.01,
"learning_rate": 4.5984637992404165e-05,
"loss": 3.9155,
"step": 245248
},
{
"epoch": 0.01,
"learning_rate": 4.5976252044893645e-05,
"loss": 3.9104,
"step": 245760
},
{
"epoch": 0.01,
"learning_rate": 4.596788247618686e-05,
"loss": 3.9049,
"step": 246272
},
{
"epoch": 0.01,
"learning_rate": 4.595949652867634e-05,
"loss": 3.9006,
"step": 246784
},
{
"epoch": 0.01,
"learning_rate": 4.595111058116582e-05,
"loss": 3.9107,
"step": 247296
},
{
"epoch": 0.01,
"learning_rate": 4.59427246336553e-05,
"loss": 3.8988,
"step": 247808
},
{
"epoch": 0.01,
"learning_rate": 4.593435506494851e-05,
"loss": 3.9094,
"step": 248320
},
{
"epoch": 0.01,
"learning_rate": 4.592596911743799e-05,
"loss": 3.9007,
"step": 248832
},
{
"epoch": 0.01,
"learning_rate": 4.591758316992747e-05,
"loss": 3.8862,
"step": 249344
},
{
"epoch": 0.01,
"learning_rate": 4.590919722241695e-05,
"loss": 3.8923,
"step": 249856
},
{
"epoch": 0.01,
"learning_rate": 4.590081127490643e-05,
"loss": 3.8889,
"step": 250368
},
{
"epoch": 0.01,
"learning_rate": 4.589242532739591e-05,
"loss": 3.9023,
"step": 250880
},
{
"epoch": 0.01,
"learning_rate": 4.588405575868912e-05,
"loss": 3.893,
"step": 251392
},
{
"epoch": 0.01,
"learning_rate": 4.58756698111786e-05,
"loss": 3.8934,
"step": 251904
},
{
"epoch": 0.01,
"learning_rate": 4.586728386366808e-05,
"loss": 3.8929,
"step": 252416
},
{
"epoch": 0.01,
"learning_rate": 4.585889791615756e-05,
"loss": 3.8963,
"step": 252928
},
{
"epoch": 0.01,
"learning_rate": 4.5850528347450774e-05,
"loss": 3.9066,
"step": 253440
},
{
"epoch": 0.01,
"learning_rate": 4.5842142399940254e-05,
"loss": 3.8879,
"step": 253952
},
{
"epoch": 0.01,
"learning_rate": 4.5833756452429734e-05,
"loss": 3.8866,
"step": 254464
},
{
"epoch": 0.01,
"learning_rate": 4.5825370504919214e-05,
"loss": 3.8932,
"step": 254976
},
{
"epoch": 0.01,
"learning_rate": 4.5817000936212423e-05,
"loss": 3.9029,
"step": 255488
},
{
"epoch": 0.01,
"learning_rate": 4.58086149887019e-05,
"loss": 3.8832,
"step": 256000
},
{
"epoch": 0.01,
"learning_rate": 4.580022904119138e-05,
"loss": 3.8951,
"step": 256512
},
{
"epoch": 0.01,
"learning_rate": 4.579184309368086e-05,
"loss": 3.8804,
"step": 257024
},
{
"epoch": 0.01,
"learning_rate": 4.578345714617034e-05,
"loss": 3.8885,
"step": 257536
},
{
"epoch": 0.01,
"learning_rate": 4.577508757746355e-05,
"loss": 3.8978,
"step": 258048
},
{
"epoch": 0.01,
"learning_rate": 4.576670162995303e-05,
"loss": 3.8815,
"step": 258560
},
{
"epoch": 0.01,
"learning_rate": 4.575831568244251e-05,
"loss": 3.8957,
"step": 259072
},
{
"epoch": 0.01,
"learning_rate": 4.574992973493199e-05,
"loss": 3.8903,
"step": 259584
},
{
"epoch": 0.01,
"learning_rate": 4.574154378742148e-05,
"loss": 3.8676,
"step": 260096
},
{
"epoch": 0.01,
"learning_rate": 4.573315783991096e-05,
"loss": 3.8853,
"step": 260608
},
{
"epoch": 0.01,
"learning_rate": 4.572478827120417e-05,
"loss": 3.8881,
"step": 261120
},
{
"epoch": 0.01,
"learning_rate": 4.571640232369365e-05,
"loss": 3.8891,
"step": 261632
},
{
"epoch": 0.01,
"learning_rate": 4.570801637618313e-05,
"loss": 3.8796,
"step": 262144
},
{
"epoch": 0.01,
"learning_rate": 4.569963042867261e-05,
"loss": 3.883,
"step": 262656
},
{
"epoch": 0.01,
"learning_rate": 4.569126085996582e-05,
"loss": 3.8679,
"step": 263168
},
{
"epoch": 0.01,
"learning_rate": 4.56828749124553e-05,
"loss": 3.8892,
"step": 263680
},
{
"epoch": 0.01,
"learning_rate": 4.567448896494478e-05,
"loss": 3.8693,
"step": 264192
},
{
"epoch": 0.01,
"learning_rate": 4.566610301743426e-05,
"loss": 3.8801,
"step": 264704
},
{
"epoch": 0.01,
"learning_rate": 4.5657733448727466e-05,
"loss": 3.8876,
"step": 265216
},
{
"epoch": 0.01,
"learning_rate": 4.5649347501216946e-05,
"loss": 3.8767,
"step": 265728
},
{
"epoch": 0.01,
"learning_rate": 4.564096155370643e-05,
"loss": 3.8867,
"step": 266240
},
{
"epoch": 0.01,
"learning_rate": 4.563257560619591e-05,
"loss": 3.8927,
"step": 266752
},
{
"epoch": 0.01,
"learning_rate": 4.5624189658685386e-05,
"loss": 3.8877,
"step": 267264
},
{
"epoch": 0.01,
"learning_rate": 4.56158200899786e-05,
"loss": 3.8956,
"step": 267776
},
{
"epoch": 0.01,
"learning_rate": 4.560743414246808e-05,
"loss": 3.8738,
"step": 268288
},
{
"epoch": 0.01,
"learning_rate": 4.5599048194957555e-05,
"loss": 3.87,
"step": 268800
},
{
"epoch": 0.01,
"learning_rate": 4.5590662247447035e-05,
"loss": 3.8741,
"step": 269312
},
{
"epoch": 0.01,
"learning_rate": 4.5582276299936515e-05,
"loss": 3.8926,
"step": 269824
},
{
"epoch": 0.01,
"learning_rate": 4.557390673122973e-05,
"loss": 3.8782,
"step": 270336
},
{
"epoch": 0.01,
"learning_rate": 4.5565520783719204e-05,
"loss": 3.8682,
"step": 270848
},
{
"epoch": 0.01,
"learning_rate": 4.5557134836208684e-05,
"loss": 3.8639,
"step": 271360
},
{
"epoch": 0.01,
"learning_rate": 4.554874888869817e-05,
"loss": 3.8725,
"step": 271872
},
{
"epoch": 0.01,
"learning_rate": 4.554036294118765e-05,
"loss": 3.8676,
"step": 272384
},
{
"epoch": 0.01,
"learning_rate": 4.553199337248086e-05,
"loss": 3.8709,
"step": 272896
},
{
"epoch": 0.01,
"learning_rate": 4.552360742497034e-05,
"loss": 3.8801,
"step": 273408
},
{
"epoch": 0.01,
"learning_rate": 4.551522147745982e-05,
"loss": 3.8832,
"step": 273920
},
{
"epoch": 0.01,
"learning_rate": 4.55068355299493e-05,
"loss": 3.873,
"step": 274432
},
{
"epoch": 0.02,
"learning_rate": 4.549846596124251e-05,
"loss": 3.8724,
"step": 274944
},
{
"epoch": 0.02,
"learning_rate": 4.549008001373199e-05,
"loss": 3.8614,
"step": 275456
},
{
"epoch": 0.02,
"learning_rate": 4.548169406622147e-05,
"loss": 3.8695,
"step": 275968
},
{
"epoch": 0.02,
"learning_rate": 4.547330811871095e-05,
"loss": 3.8708,
"step": 276480
},
{
"epoch": 0.02,
"learning_rate": 4.546493855000416e-05,
"loss": 3.8691,
"step": 276992
},
{
"epoch": 0.02,
"learning_rate": 4.545655260249364e-05,
"loss": 3.8634,
"step": 277504
},
{
"epoch": 0.02,
"learning_rate": 4.5448166654983124e-05,
"loss": 3.8761,
"step": 278016
},
{
"epoch": 0.02,
"learning_rate": 4.5439780707472604e-05,
"loss": 3.8694,
"step": 278528
},
{
"epoch": 0.02,
"learning_rate": 4.543141113876581e-05,
"loss": 3.8814,
"step": 279040
},
{
"epoch": 0.02,
"learning_rate": 4.542302519125529e-05,
"loss": 3.8713,
"step": 279552
},
{
"epoch": 0.02,
"learning_rate": 4.541463924374477e-05,
"loss": 3.8766,
"step": 280064
},
{
"epoch": 0.02,
"learning_rate": 4.540625329623425e-05,
"loss": 3.8706,
"step": 280576
},
{
"epoch": 0.02,
"learning_rate": 4.539788372752746e-05,
"loss": 3.8656,
"step": 281088
},
{
"epoch": 0.02,
"learning_rate": 4.538949778001694e-05,
"loss": 3.8841,
"step": 281600
},
{
"epoch": 0.02,
"learning_rate": 4.538111183250642e-05,
"loss": 3.8636,
"step": 282112
},
{
"epoch": 0.02,
"learning_rate": 4.53727258849959e-05,
"loss": 3.8837,
"step": 282624
},
{
"epoch": 0.02,
"learning_rate": 4.536435631628911e-05,
"loss": 3.8573,
"step": 283136
},
{
"epoch": 0.02,
"learning_rate": 4.535597036877859e-05,
"loss": 3.8587,
"step": 283648
},
{
"epoch": 0.02,
"learning_rate": 4.534758442126808e-05,
"loss": 3.8599,
"step": 284160
},
{
"epoch": 0.02,
"learning_rate": 4.533919847375756e-05,
"loss": 3.8747,
"step": 284672
},
{
"epoch": 0.02,
"learning_rate": 4.533082890505077e-05,
"loss": 3.8657,
"step": 285184
},
{
"epoch": 0.02,
"learning_rate": 4.532244295754025e-05,
"loss": 3.8524,
"step": 285696
},
{
"epoch": 0.02,
"learning_rate": 4.531405701002973e-05,
"loss": 3.8513,
"step": 286208
},
{
"epoch": 0.02,
"learning_rate": 4.530567106251921e-05,
"loss": 3.8615,
"step": 286720
},
{
"epoch": 0.02,
"learning_rate": 4.529728511500869e-05,
"loss": 3.8777,
"step": 287232
},
{
"epoch": 0.02,
"learning_rate": 4.5288915546301896e-05,
"loss": 3.8614,
"step": 287744
},
{
"epoch": 0.02,
"learning_rate": 4.5280529598791376e-05,
"loss": 3.8788,
"step": 288256
},
{
"epoch": 0.02,
"learning_rate": 4.5272143651280856e-05,
"loss": 3.8625,
"step": 288768
},
{
"epoch": 0.02,
"learning_rate": 4.5263757703770336e-05,
"loss": 3.8655,
"step": 289280
},
{
"epoch": 0.02,
"learning_rate": 4.5255388135063545e-05,
"loss": 3.8669,
"step": 289792
},
{
"epoch": 0.02,
"learning_rate": 4.524700218755303e-05,
"loss": 3.8565,
"step": 290304
},
{
"epoch": 0.02,
"learning_rate": 4.523861624004251e-05,
"loss": 3.8563,
"step": 290816
},
{
"epoch": 0.02,
"learning_rate": 4.523023029253199e-05,
"loss": 3.8607,
"step": 291328
},
{
"epoch": 0.02,
"learning_rate": 4.522184434502147e-05,
"loss": 3.8582,
"step": 291840
},
{
"epoch": 0.02,
"learning_rate": 4.521347477631468e-05,
"loss": 3.8598,
"step": 292352
},
{
"epoch": 0.02,
"learning_rate": 4.520508882880416e-05,
"loss": 3.8629,
"step": 292864
},
{
"epoch": 0.02,
"learning_rate": 4.519670288129364e-05,
"loss": 3.8645,
"step": 293376
},
{
"epoch": 0.02,
"learning_rate": 4.518831693378312e-05,
"loss": 3.852,
"step": 293888
},
{
"epoch": 0.02,
"learning_rate": 4.517994736507633e-05,
"loss": 3.8532,
"step": 294400
},
{
"epoch": 0.02,
"learning_rate": 4.517156141756581e-05,
"loss": 3.8748,
"step": 294912
},
{
"epoch": 0.02,
"learning_rate": 4.516317547005529e-05,
"loss": 3.8532,
"step": 295424
},
{
"epoch": 0.02,
"learning_rate": 4.515478952254477e-05,
"loss": 3.8684,
"step": 295936
},
{
"epoch": 0.02,
"learning_rate": 4.514640357503425e-05,
"loss": 3.8625,
"step": 296448
},
{
"epoch": 0.02,
"learning_rate": 4.5138034006327465e-05,
"loss": 3.8635,
"step": 296960
},
{
"epoch": 0.02,
"learning_rate": 4.5129648058816945e-05,
"loss": 3.8537,
"step": 297472
},
{
"epoch": 0.02,
"learning_rate": 4.5121262111306425e-05,
"loss": 3.8563,
"step": 297984
},
{
"epoch": 0.02,
"learning_rate": 4.5112876163795905e-05,
"loss": 3.8565,
"step": 298496
},
{
"epoch": 0.02,
"learning_rate": 4.5104506595089114e-05,
"loss": 3.8602,
"step": 299008
},
{
"epoch": 0.02,
"learning_rate": 4.5096120647578594e-05,
"loss": 3.8743,
"step": 299520
},
{
"epoch": 0.02,
"learning_rate": 4.5087734700068074e-05,
"loss": 3.8604,
"step": 300032
},
{
"epoch": 0.02,
"learning_rate": 4.5079348752557554e-05,
"loss": 3.8658,
"step": 300544
},
{
"epoch": 0.02,
"learning_rate": 4.507097918385076e-05,
"loss": 3.8636,
"step": 301056
},
{
"epoch": 0.02,
"learning_rate": 4.506259323634024e-05,
"loss": 3.8489,
"step": 301568
},
{
"epoch": 0.02,
"learning_rate": 4.505420728882972e-05,
"loss": 3.8572,
"step": 302080
},
{
"epoch": 0.02,
"learning_rate": 4.50458213413192e-05,
"loss": 3.8483,
"step": 302592
},
{
"epoch": 0.02,
"learning_rate": 4.503745177261242e-05,
"loss": 3.8531,
"step": 303104
},
{
"epoch": 0.02,
"learning_rate": 4.50290658251019e-05,
"loss": 3.8544,
"step": 303616
},
{
"epoch": 0.02,
"learning_rate": 4.502067987759138e-05,
"loss": 3.8501,
"step": 304128
},
{
"epoch": 0.02,
"learning_rate": 4.501229393008086e-05,
"loss": 3.848,
"step": 304640
},
{
"epoch": 0.02,
"learning_rate": 4.500392436137407e-05,
"loss": 3.8541,
"step": 305152
},
{
"epoch": 0.03,
"eval_loss": 3.9159610271453857,
"eval_runtime": 566.2921,
"eval_samples_per_second": 673.841,
"eval_steps_per_second": 21.058,
"step": 305276
},
{
"epoch": 0.0,
"learning_rate": 4.499553841386355e-05,
"loss": 3.8595,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498715246635303e-05,
"loss": 3.8573,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497876651884251e-05,
"loss": 3.853,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497038057133199e-05,
"loss": 3.8488,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496199462382146e-05,
"loss": 3.8587,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495360867631094e-05,
"loss": 3.8354,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494522272880042e-05,
"loss": 3.8544,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.49368367812899e-05,
"loss": 3.8441,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928467212583116e-05,
"loss": 3.8414,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920081265072596e-05,
"loss": 3.8497,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911695317562076e-05,
"loss": 3.8534,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903309370051556e-05,
"loss": 3.8358,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4894939801344765e-05,
"loss": 3.8433,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886553853834245e-05,
"loss": 3.8429,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878167906323725e-05,
"loss": 3.8473,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869781958813205e-05,
"loss": 3.8305,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861412390106414e-05,
"loss": 3.835,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853026442595894e-05,
"loss": 3.8385,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844640495085374e-05,
"loss": 3.8391,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836254547574854e-05,
"loss": 3.8492,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482788497886807e-05,
"loss": 3.8408,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481949903135755e-05,
"loss": 3.8554,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481111308384703e-05,
"loss": 3.849,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480272713633651e-05,
"loss": 3.8434,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479435756762972e-05,
"loss": 3.8385,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.47859716201192e-05,
"loss": 3.8404,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477758567260868e-05,
"loss": 3.8482,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476919972509816e-05,
"loss": 3.8368,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476083015639137e-05,
"loss": 3.8398,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475244420888085e-05,
"loss": 3.8395,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474405826137033e-05,
"loss": 3.8286,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473567231385981e-05,
"loss": 3.8452,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727302745153024e-05,
"loss": 3.8499,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718916797642504e-05,
"loss": 3.8394,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710530850131984e-05,
"loss": 3.8344,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4702144902621464e-05,
"loss": 3.8415,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469377533391467e-05,
"loss": 3.8389,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468538938640415e-05,
"loss": 3.8383,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467700343889363e-05,
"loss": 3.8345,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466861749138311e-05,
"loss": 3.8209,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466024792267632e-05,
"loss": 3.8272,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.46518619751658e-05,
"loss": 3.822,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464347602765528e-05,
"loss": 3.8379,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463509008014476e-05,
"loss": 3.8281,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462672051143798e-05,
"loss": 3.8294,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461833456392746e-05,
"loss": 3.8279,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460994861641694e-05,
"loss": 3.8307,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460156266890642e-05,
"loss": 3.8435,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593193100199626e-05,
"loss": 3.8242,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584807152689106e-05,
"loss": 3.8199,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576421205178586e-05,
"loss": 3.8306,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568035257668066e-05,
"loss": 3.8344,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559665688961275e-05,
"loss": 3.8232,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551279741450755e-05,
"loss": 3.8274,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542893793940235e-05,
"loss": 3.8201,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534507846429715e-05,
"loss": 3.8244,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452613827772293e-05,
"loss": 3.8328,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451775233021241e-05,
"loss": 3.8158,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450936638270189e-05,
"loss": 3.8347,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450098043519137e-05,
"loss": 3.8245,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449261086648458e-05,
"loss": 3.8085,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448422491897406e-05,
"loss": 3.8192,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447583897146354e-05,
"loss": 3.8259,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446745302395302e-05,
"loss": 3.8321,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445908345524623e-05,
"loss": 3.8159,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445069750773571e-05,
"loss": 3.8217,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444231156022519e-05,
"loss": 3.8022,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443392561271467e-05,
"loss": 3.8266,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425556044007885e-05,
"loss": 3.8114,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.4417170096497365e-05,
"loss": 3.8174,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.4408784148986845e-05,
"loss": 3.8263,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400398201476325e-05,
"loss": 3.8156,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4392028632769534e-05,
"loss": 3.8214,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.4383642685259014e-05,
"loss": 3.8307,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.4375256737748494e-05,
"loss": 3.826,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.4366870790237974e-05,
"loss": 3.8312,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435850122153118e-05,
"loss": 3.816,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435011527402066e-05,
"loss": 3.8102,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434172932651014e-05,
"loss": 3.8146,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433334337899962e-05,
"loss": 3.8297,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432497381029284e-05,
"loss": 3.817,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431658786278232e-05,
"loss": 3.8097,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.43082019152718e-05,
"loss": 3.801,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429981596776128e-05,
"loss": 3.8144,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429144639905449e-05,
"loss": 3.8046,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428306045154397e-05,
"loss": 3.8164,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427467450403345e-05,
"loss": 3.8152,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426628855652293e-05,
"loss": 3.8258,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257918987816136e-05,
"loss": 3.8118,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249533040305616e-05,
"loss": 3.8141,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241147092795096e-05,
"loss": 3.8012,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232761145284576e-05,
"loss": 3.8105,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422439157657779e-05,
"loss": 3.8145,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421600562906727e-05,
"loss": 3.8076,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420761968155675e-05,
"loss": 3.8059,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419923373404623e-05,
"loss": 3.819,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419086416533944e-05,
"loss": 3.8069,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418247821782892e-05,
"loss": 3.8285,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.41740922703184e-05,
"loss": 3.8099,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416570632280788e-05,
"loss": 3.8172,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415733675410109e-05,
"loss": 3.8105,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414895080659057e-05,
"loss": 3.8067,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414056485908005e-05,
"loss": 3.8259,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413217891156953e-05,
"loss": 3.8043,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123809342862746e-05,
"loss": 3.8233,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115423395352226e-05,
"loss": 3.8015,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107037447841706e-05,
"loss": 3.8036,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098651500331186e-05,
"loss": 3.7995,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090281931624395e-05,
"loss": 3.8133,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081895984113875e-05,
"loss": 3.8119,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073510036603355e-05,
"loss": 3.7984,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065124089092835e-05,
"loss": 3.7902,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056754520386044e-05,
"loss": 3.8034,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048368572875524e-05,
"loss": 3.821,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4039982625365004e-05,
"loss": 3.8011,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031596677854484e-05,
"loss": 3.8213,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.40232271091477e-05,
"loss": 3.807,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401484116163718e-05,
"loss": 3.8092,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400645521412666e-05,
"loss": 3.8127,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399806926661613e-05,
"loss": 3.8004,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398969969790935e-05,
"loss": 3.7988,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398131375039883e-05,
"loss": 3.8038,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397292780288831e-05,
"loss": 3.8042,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396454185537778e-05,
"loss": 3.803,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956172286671e-05,
"loss": 3.8049,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394778633916048e-05,
"loss": 3.8085,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393940039164996e-05,
"loss": 3.7962,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393101444413944e-05,
"loss": 3.7975,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392264487543265e-05,
"loss": 3.8143,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391425892792213e-05,
"loss": 3.7978,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905872980411606e-05,
"loss": 3.8125,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897487032901086e-05,
"loss": 3.8108,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.38891174641943e-05,
"loss": 3.8048,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388073151668378e-05,
"loss": 3.8021,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872345569173255e-05,
"loss": 3.8,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863959621662735e-05,
"loss": 3.8015,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385559005295595e-05,
"loss": 3.8038,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847204105445424e-05,
"loss": 3.817,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383881815793491e-05,
"loss": 3.8095,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383043221042439e-05,
"loss": 3.8093,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382206264171761e-05,
"loss": 3.8086,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381367669420708e-05,
"loss": 3.796,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380529074669656e-05,
"loss": 3.8015,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379690479918604e-05,
"loss": 3.7937,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788551609282985e-05,
"loss": 3.7991,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780165661772465e-05,
"loss": 3.8024,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771779714261945e-05,
"loss": 3.7955,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763393766751425e-05,
"loss": 3.7904,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550078192409e-05,
"loss": 3.8015,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.891148805618286,
"eval_runtime": 571.8978,
"eval_samples_per_second": 667.236,
"eval_steps_per_second": 20.852,
"step": 381595
},
{
"epoch": 0.0,
"learning_rate": 4.374662187173038e-05,
"loss": 3.8075,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.3738235924219865e-05,
"loss": 3.8014,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.3729849976709345e-05,
"loss": 3.8007,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.3721464029198824e-05,
"loss": 3.7977,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.3713078081688304e-05,
"loss": 3.8,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.3704692134177784e-05,
"loss": 3.7856,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.3696306186667264e-05,
"loss": 3.7983,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.3687920239156744e-05,
"loss": 3.7881,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.3679550670449953e-05,
"loss": 3.7936,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.367118110174316e-05,
"loss": 3.7968,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366279515423264e-05,
"loss": 3.799,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365440920672212e-05,
"loss": 3.7827,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.36460232592116e-05,
"loss": 3.7929,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363763731170108e-05,
"loss": 3.7875,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362925136419056e-05,
"loss": 3.794,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362086541668005e-05,
"loss": 3.781,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361247946916953e-05,
"loss": 3.7814,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360410990046274e-05,
"loss": 3.7854,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359572395295222e-05,
"loss": 3.7888,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.35873380054417e-05,
"loss": 3.7982,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357895205793118e-05,
"loss": 3.7865,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.357058248922439e-05,
"loss": 3.8057,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.356219654171387e-05,
"loss": 3.7933,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.355381059420335e-05,
"loss": 3.7938,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354542464669283e-05,
"loss": 3.7863,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.3537055077986036e-05,
"loss": 3.7871,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.3528669130475516e-05,
"loss": 3.7975,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.3520283182964996e-05,
"loss": 3.7841,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351189723545448e-05,
"loss": 3.7895,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350352766674769e-05,
"loss": 3.7861,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.349514171923717e-05,
"loss": 3.7761,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348675577172665e-05,
"loss": 3.7958,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347836982421613e-05,
"loss": 3.7949,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.347000025550934e-05,
"loss": 3.792,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346161430799882e-05,
"loss": 3.7812,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.34532283604883e-05,
"loss": 3.7924,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344484241297778e-05,
"loss": 3.7817,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343647284427099e-05,
"loss": 3.7917,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.342808689676047e-05,
"loss": 3.7845,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341970094924995e-05,
"loss": 3.7697,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3411315001739436e-05,
"loss": 3.777,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402945433032645e-05,
"loss": 3.7685,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394559485522125e-05,
"loss": 3.791,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3386173538011605e-05,
"loss": 3.7781,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377787590501085e-05,
"loss": 3.7735,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3369418021794294e-05,
"loss": 3.782,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3361032074283774e-05,
"loss": 3.7813,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.3352646126773254e-05,
"loss": 3.7924,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.3344260179262734e-05,
"loss": 3.7721,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333589061055594e-05,
"loss": 3.773,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332750466304542e-05,
"loss": 3.7822,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.33191187155349e-05,
"loss": 3.7809,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331073276802439e-05,
"loss": 3.7742,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.33023631993176e-05,
"loss": 3.7758,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329397725180708e-05,
"loss": 3.7718,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328559130429656e-05,
"loss": 3.7789,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327720535678604e-05,
"loss": 3.7797,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326883578807925e-05,
"loss": 3.7731,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326044984056873e-05,
"loss": 3.7849,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325206389305821e-05,
"loss": 3.7735,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324367794554768e-05,
"loss": 3.7643,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.32353083768409e-05,
"loss": 3.7699,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322692242933038e-05,
"loss": 3.7698,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321853648181986e-05,
"loss": 3.7907,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321015053430934e-05,
"loss": 3.7675,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320178096560255e-05,
"loss": 3.7727,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319339501809203e-05,
"loss": 3.7568,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.3185009070581506e-05,
"loss": 3.7747,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.3176623123070986e-05,
"loss": 3.765,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.31682535543642e-05,
"loss": 3.766,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315986760685368e-05,
"loss": 3.778,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.3151481659343155e-05,
"loss": 3.7696,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314311209063637e-05,
"loss": 3.7726,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313472614312585e-05,
"loss": 3.7824,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312634019561533e-05,
"loss": 3.7763,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.3117970626908546e-05,
"loss": 3.7864,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.3109584679398026e-05,
"loss": 3.7691,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101198731887506e-05,
"loss": 3.7608,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309281278437698e-05,
"loss": 3.767,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308442683686646e-05,
"loss": 3.7827,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307604088935594e-05,
"loss": 3.769,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.306765494184542e-05,
"loss": 3.7642,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.30592689943349e-05,
"loss": 3.7537,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.305089942562811e-05,
"loss": 3.7683,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042529856921324e-05,
"loss": 3.7536,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.3034143909410804e-05,
"loss": 3.7687,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.3025757961900284e-05,
"loss": 3.7705,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.3017372014389764e-05,
"loss": 3.7755,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.3008986066879244e-05,
"loss": 3.7691,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.3000600119368724e-05,
"loss": 3.7681,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.2992214171858204e-05,
"loss": 3.7549,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.2983828224347684e-05,
"loss": 3.7652,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297545865564089e-05,
"loss": 3.7661,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.296707270813037e-05,
"loss": 3.764,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295868676061985e-05,
"loss": 3.7585,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.295030081310933e-05,
"loss": 3.7751,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294193124440254e-05,
"loss": 3.7603,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293354529689202e-05,
"loss": 3.7858,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.29251593493815e-05,
"loss": 3.7587,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291677340187099e-05,
"loss": 3.7743,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.29084038331642e-05,
"loss": 3.7624,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.290001788565368e-05,
"loss": 3.7626,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289163193814316e-05,
"loss": 3.7819,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288324599063264e-05,
"loss": 3.7576,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287487642192585e-05,
"loss": 3.7778,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.286649047441533e-05,
"loss": 3.7572,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.285810452690481e-05,
"loss": 3.7577,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284971857939429e-05,
"loss": 3.7537,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.2841349010687496e-05,
"loss": 3.7688,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283297944198071e-05,
"loss": 3.7664,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282459349447019e-05,
"loss": 3.7566,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281620754695967e-05,
"loss": 3.7426,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280782159944915e-05,
"loss": 3.7596,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279943565193863e-05,
"loss": 3.773,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279104970442811e-05,
"loss": 3.7652,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278268013572132e-05,
"loss": 3.7709,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.27742941882108e-05,
"loss": 3.7632,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276590824070028e-05,
"loss": 3.7634,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275752229318976e-05,
"loss": 3.7674,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.274913634567924e-05,
"loss": 3.7582,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274075039816872e-05,
"loss": 3.7529,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.27323644506582e-05,
"loss": 3.758,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.272397850314768e-05,
"loss": 3.7596,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.2715608934440896e-05,
"loss": 3.7593,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.2707222986930376e-05,
"loss": 3.7597,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.2698837039419856e-05,
"loss": 3.764,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690451091909336e-05,
"loss": 3.7573,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.2682081523202545e-05,
"loss": 3.7513,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.2673695575692025e-05,
"loss": 3.7685,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.2665309628181505e-05,
"loss": 3.7541,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.2656923680670985e-05,
"loss": 3.7676,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.2648554111964194e-05,
"loss": 3.7697,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.2640168164453674e-05,
"loss": 3.7592,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.2631782216943154e-05,
"loss": 3.7603,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.2623396269432634e-05,
"loss": 3.7584,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261502670072584e-05,
"loss": 3.7551,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260664075321533e-05,
"loss": 3.756,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259825480570481e-05,
"loss": 3.7718,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258986885819429e-05,
"loss": 3.7708,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.25814992894875e-05,
"loss": 3.7615,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257311334197698e-05,
"loss": 3.7655,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.256472739446646e-05,
"loss": 3.7561,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.255635782575967e-05,
"loss": 3.7598,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.254797187824915e-05,
"loss": 3.7538,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253958593073863e-05,
"loss": 3.7484,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253119998322811e-05,
"loss": 3.7618,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252281403571758e-05,
"loss": 3.7534,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251442808820707e-05,
"loss": 3.7467,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250605851950028e-05,
"loss": 3.7558,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.87520694732666,
"eval_runtime": 669.5577,
"eval_samples_per_second": 569.915,
"eval_steps_per_second": 17.81,
"step": 457914
},
{
"epoch": 0.0,
"learning_rate": 4.249767257198976e-05,
"loss": 3.7637,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.2489286624479237e-05,
"loss": 3.7592,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.2480900676968716e-05,
"loss": 3.7573,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.2472514729458196e-05,
"loss": 3.7559,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.2464128781947676e-05,
"loss": 3.7586,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.2455759213240885e-05,
"loss": 3.7441,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.2447373265730365e-05,
"loss": 3.7573,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.2438987318219845e-05,
"loss": 3.7437,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.2430601370709325e-05,
"loss": 3.7495,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.2422215423198805e-05,
"loss": 3.7532,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241384585449202e-05,
"loss": 3.7601,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.24054599069815e-05,
"loss": 3.7355,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239707395947098e-05,
"loss": 3.7527,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238868801196046e-05,
"loss": 3.7445,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238030206444994e-05,
"loss": 3.7542,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237191611693942e-05,
"loss": 3.7366,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.23635301694289e-05,
"loss": 3.7386,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235516060072211e-05,
"loss": 3.7467,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234677465321159e-05,
"loss": 3.745,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233838870570107e-05,
"loss": 3.7548,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.233000275819055e-05,
"loss": 3.7477,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232163318948376e-05,
"loss": 3.7621,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231324724197324e-05,
"loss": 3.7538,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230486129446272e-05,
"loss": 3.7489,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296475346952206e-05,
"loss": 3.7433,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2288105778245415e-05,
"loss": 3.7474,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279719830734895e-05,
"loss": 3.7547,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2271333883224375e-05,
"loss": 3.7464,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2262947935713855e-05,
"loss": 3.7453,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254578367007064e-05,
"loss": 3.7481,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2246192419496544e-05,
"loss": 3.736,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.2237806471986024e-05,
"loss": 3.7519,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.2229420524475504e-05,
"loss": 3.7558,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222105095576871e-05,
"loss": 3.7506,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221266500825819e-05,
"loss": 3.7386,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220427906074767e-05,
"loss": 3.7523,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219589311323716e-05,
"loss": 3.7422,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218752354453037e-05,
"loss": 3.7483,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217913759701985e-05,
"loss": 3.7469,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217075164950933e-05,
"loss": 3.7326,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216236570199881e-05,
"loss": 3.7326,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215399613329202e-05,
"loss": 3.7268,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.21456101857815e-05,
"loss": 3.7559,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213722423827098e-05,
"loss": 3.7359,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.2128854669564186e-05,
"loss": 3.7329,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.2120468722053666e-05,
"loss": 3.7449,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.2112082774543146e-05,
"loss": 3.7396,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103696827032626e-05,
"loss": 3.7484,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209531087952211e-05,
"loss": 3.7329,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208692493201159e-05,
"loss": 3.7374,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207853898450107e-05,
"loss": 3.7382,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070153036990546e-05,
"loss": 3.7429,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.206178346828376e-05,
"loss": 3.7356,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.205339752077324e-05,
"loss": 3.7319,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204501157326272e-05,
"loss": 3.7352,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.2036625625752195e-05,
"loss": 3.74,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202825605704541e-05,
"loss": 3.7379,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201988648833862e-05,
"loss": 3.7325,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.20115005408281e-05,
"loss": 3.7456,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200311459331758e-05,
"loss": 3.7343,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199472864580707e-05,
"loss": 3.7242,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.1986342698296547e-05,
"loss": 3.7287,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197795675078602e-05,
"loss": 3.7311,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.19695708032755e-05,
"loss": 3.7509,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196118485576498e-05,
"loss": 3.7303,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195281528705819e-05,
"loss": 3.7326,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194442933954767e-05,
"loss": 3.7194,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193604339203715e-05,
"loss": 3.7335,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192765744452663e-05,
"loss": 3.7273,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191928787581984e-05,
"loss": 3.7288,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191090192830932e-05,
"loss": 3.7358,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902515980798804e-05,
"loss": 3.7289,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1894130033288284e-05,
"loss": 3.738,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885744085777764e-05,
"loss": 3.7431,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1877358138267244e-05,
"loss": 3.7378,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.186898856956045e-05,
"loss": 3.745,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186060262204993e-05,
"loss": 3.736,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.185221667453941e-05,
"loss": 3.7204,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.184383072702889e-05,
"loss": 3.7277,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183544477951837e-05,
"loss": 3.7387,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182705883200785e-05,
"loss": 3.7335,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181867288449733e-05,
"loss": 3.7295,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.181028693698681e-05,
"loss": 3.7112,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180191736828002e-05,
"loss": 3.7324,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179354779957324e-05,
"loss": 3.7154,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178516185206272e-05,
"loss": 3.732,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.17767759045522e-05,
"loss": 3.7286,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176838995704168e-05,
"loss": 3.739,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.176000400953116e-05,
"loss": 3.7289,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175161806202064e-05,
"loss": 3.7295,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174323211451012e-05,
"loss": 3.7189,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.17348461669996e-05,
"loss": 3.7325,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172647659829281e-05,
"loss": 3.7241,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.1718107029586016e-05,
"loss": 3.7272,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.1709721082075496e-05,
"loss": 3.7196,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.1701335134564976e-05,
"loss": 3.7334,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.1692949187054456e-05,
"loss": 3.7215,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.1684563239543936e-05,
"loss": 3.7498,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167617729203342e-05,
"loss": 3.7221,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166780772332663e-05,
"loss": 3.7372,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165942177581611e-05,
"loss": 3.728,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165103582830559e-05,
"loss": 3.7224,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164264988079507e-05,
"loss": 3.7429,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.163426393328455e-05,
"loss": 3.7239,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625877985774025e-05,
"loss": 3.7373,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617492038263505e-05,
"loss": 3.7236,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1609106090752984e-05,
"loss": 3.7183,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.16007365220462e-05,
"loss": 3.718,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159236695333941e-05,
"loss": 3.7317,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158398100582889e-05,
"loss": 3.7297,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.1575595058318376e-05,
"loss": 3.7233,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.1567209110807856e-05,
"loss": 3.7003,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155882316329733e-05,
"loss": 3.7224,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155043721578681e-05,
"loss": 3.7362,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.1542067647080025e-05,
"loss": 3.7273,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.15336816995695e-05,
"loss": 3.7344,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152529575205898e-05,
"loss": 3.7267,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151690980454846e-05,
"loss": 3.7276,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150852385703794e-05,
"loss": 3.7303,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150013790952742e-05,
"loss": 3.723,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.14917519620169e-05,
"loss": 3.7154,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148336601450638e-05,
"loss": 3.7203,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1474996445799594e-05,
"loss": 3.7226,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466610498289074e-05,
"loss": 3.7231,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1458224550778554e-05,
"loss": 3.7228,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.144985498207176e-05,
"loss": 3.7278,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.144146903456124e-05,
"loss": 3.7186,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.143308308705072e-05,
"loss": 3.7156,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.14246971395402e-05,
"loss": 3.7316,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.141631119202968e-05,
"loss": 3.7182,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140792524451916e-05,
"loss": 3.7324,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139955567581237e-05,
"loss": 3.7328,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139116972830185e-05,
"loss": 3.7229,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138278378079133e-05,
"loss": 3.724,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.137439783328081e-05,
"loss": 3.7245,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136601188577029e-05,
"loss": 3.7178,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135762593825978e-05,
"loss": 3.7201,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134923999074926e-05,
"loss": 3.737,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134087042204247e-05,
"loss": 3.7335,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133248447453195e-05,
"loss": 3.728,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132409852702143e-05,
"loss": 3.7288,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131571257951091e-05,
"loss": 3.7185,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.1307343010804116e-05,
"loss": 3.7238,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.1298957063293596e-05,
"loss": 3.7174,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.1290571115783076e-05,
"loss": 3.7115,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.1282185168272556e-05,
"loss": 3.7295,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.1273799220762036e-05,
"loss": 3.7167,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.1265413273251516e-05,
"loss": 3.7119,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.1257027325740996e-05,
"loss": 3.7219,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.865478992462158,
"eval_runtime": 576.716,
"eval_samples_per_second": 661.662,
"eval_steps_per_second": 20.677,
"step": 534233
},
{
"epoch": 0.0,
"learning_rate": 4.124865775703421e-05,
"loss": 3.729,
"step": 534528
},
{
"epoch": 0.0,
"learning_rate": 4.1240271809523685e-05,
"loss": 3.7204,
"step": 535040
},
{
"epoch": 0.0,
"learning_rate": 4.1231885862013165e-05,
"loss": 3.7264,
"step": 535552
},
{
"epoch": 0.0,
"learning_rate": 4.1223499914502645e-05,
"loss": 3.721,
"step": 536064
},
{
"epoch": 0.0,
"learning_rate": 4.1215113966992125e-05,
"loss": 3.7189,
"step": 536576
},
{
"epoch": 0.0,
"learning_rate": 4.1206728019481605e-05,
"loss": 3.7126,
"step": 537088
},
{
"epoch": 0.0,
"learning_rate": 4.1198358450774814e-05,
"loss": 3.7201,
"step": 537600
},
{
"epoch": 0.0,
"learning_rate": 4.1189972503264294e-05,
"loss": 3.7094,
"step": 538112
},
{
"epoch": 0.0,
"learning_rate": 4.1181586555753774e-05,
"loss": 3.7138,
"step": 538624
},
{
"epoch": 0.0,
"learning_rate": 4.1173200608243254e-05,
"loss": 3.7124,
"step": 539136
},
{
"epoch": 0.0,
"learning_rate": 4.116483103953647e-05,
"loss": 3.7259,
"step": 539648
},
{
"epoch": 0.0,
"learning_rate": 4.115644509202595e-05,
"loss": 3.7051,
"step": 540160
},
{
"epoch": 0.0,
"learning_rate": 4.114805914451543e-05,
"loss": 3.7171,
"step": 540672
},
{
"epoch": 0.0,
"learning_rate": 4.113967319700491e-05,
"loss": 3.7062,
"step": 541184
},
{
"epoch": 0.0,
"learning_rate": 4.113128724949439e-05,
"loss": 3.721,
"step": 541696
},
{
"epoch": 0.0,
"learning_rate": 4.112290130198387e-05,
"loss": 3.7042,
"step": 542208
},
{
"epoch": 0.0,
"learning_rate": 4.111451535447335e-05,
"loss": 3.7047,
"step": 542720
},
{
"epoch": 0.0,
"learning_rate": 4.110614578576656e-05,
"loss": 3.7102,
"step": 543232
},
{
"epoch": 0.0,
"learning_rate": 4.109775983825604e-05,
"loss": 3.7094,
"step": 543744
},
{
"epoch": 0.0,
"learning_rate": 4.108939026954925e-05,
"loss": 3.719,
"step": 544256
},
{
"epoch": 0.0,
"learning_rate": 4.108100432203873e-05,
"loss": 3.7108,
"step": 544768
},
{
"epoch": 0.0,
"learning_rate": 4.107261837452821e-05,
"loss": 3.7283,
"step": 545280
},
{
"epoch": 0.0,
"learning_rate": 4.106423242701769e-05,
"loss": 3.7135,
"step": 545792
},
{
"epoch": 0.0,
"learning_rate": 4.105584647950717e-05,
"loss": 3.7167,
"step": 546304
},
{
"epoch": 0.0,
"learning_rate": 4.1047460531996654e-05,
"loss": 3.7123,
"step": 546816
},
{
"epoch": 0.0,
"learning_rate": 4.1039074584486134e-05,
"loss": 3.7119,
"step": 547328
},
{
"epoch": 0.0,
"learning_rate": 4.103070501577934e-05,
"loss": 3.7172,
"step": 547840
},
{
"epoch": 0.0,
"learning_rate": 4.102231906826882e-05,
"loss": 3.7111,
"step": 548352
},
{
"epoch": 0.0,
"learning_rate": 4.10139331207583e-05,
"loss": 3.7133,
"step": 548864
},
{
"epoch": 0.0,
"learning_rate": 4.100554717324778e-05,
"loss": 3.7102,
"step": 549376
},
{
"epoch": 0.01,
"learning_rate": 4.099716122573726e-05,
"loss": 3.7025,
"step": 549888
},
{
"epoch": 0.01,
"learning_rate": 4.098879165703047e-05,
"loss": 3.7152,
"step": 550400
},
{
"epoch": 0.01,
"learning_rate": 4.098040570951995e-05,
"loss": 3.7225,
"step": 550912
},
{
"epoch": 0.01,
"learning_rate": 4.097201976200943e-05,
"loss": 3.7142,
"step": 551424
},
{
"epoch": 0.01,
"learning_rate": 4.096363381449891e-05,
"loss": 3.7071,
"step": 551936
},
{
"epoch": 0.01,
"learning_rate": 4.095526424579212e-05,
"loss": 3.716,
"step": 552448
},
{
"epoch": 0.01,
"learning_rate": 4.094687829828161e-05,
"loss": 3.7094,
"step": 552960
},
{
"epoch": 0.01,
"learning_rate": 4.093849235077109e-05,
"loss": 3.7143,
"step": 553472
},
{
"epoch": 0.01,
"learning_rate": 4.093010640326057e-05,
"loss": 3.7103,
"step": 553984
},
{
"epoch": 0.01,
"learning_rate": 4.092172045575005e-05,
"loss": 3.7012,
"step": 554496
},
{
"epoch": 0.01,
"learning_rate": 4.091335088704326e-05,
"loss": 3.7006,
"step": 555008
},
{
"epoch": 0.01,
"learning_rate": 4.090496493953274e-05,
"loss": 3.6936,
"step": 555520
},
{
"epoch": 0.01,
"learning_rate": 4.089657899202222e-05,
"loss": 3.719,
"step": 556032
},
{
"epoch": 0.01,
"learning_rate": 4.08881930445117e-05,
"loss": 3.7035,
"step": 556544
},
{
"epoch": 0.01,
"learning_rate": 4.0879823475804906e-05,
"loss": 3.6999,
"step": 557056
},
{
"epoch": 0.01,
"learning_rate": 4.0871437528294386e-05,
"loss": 3.712,
"step": 557568
},
{
"epoch": 0.01,
"learning_rate": 4.0863051580783866e-05,
"loss": 3.705,
"step": 558080
},
{
"epoch": 0.01,
"learning_rate": 4.0854665633273346e-05,
"loss": 3.7136,
"step": 558592
},
{
"epoch": 0.01,
"learning_rate": 4.0846279685762826e-05,
"loss": 3.6993,
"step": 559104
},
{
"epoch": 0.01,
"learning_rate": 4.083791011705604e-05,
"loss": 3.7062,
"step": 559616
},
{
"epoch": 0.01,
"learning_rate": 4.082952416954552e-05,
"loss": 3.7024,
"step": 560128
},
{
"epoch": 0.01,
"learning_rate": 4.0821138222034995e-05,
"loss": 3.7068,
"step": 560640
},
{
"epoch": 0.01,
"learning_rate": 4.0812752274524475e-05,
"loss": 3.7055,
"step": 561152
},
{
"epoch": 0.01,
"learning_rate": 4.080438270581769e-05,
"loss": 3.6969,
"step": 561664
},
{
"epoch": 0.01,
"learning_rate": 4.079599675830717e-05,
"loss": 3.7039,
"step": 562176
},
{
"epoch": 0.01,
"learning_rate": 4.0787610810796644e-05,
"loss": 3.7057,
"step": 562688
},
{
"epoch": 0.01,
"learning_rate": 4.0779224863286124e-05,
"loss": 3.7056,
"step": 563200
},
{
"epoch": 0.01,
"learning_rate": 4.0770838915775604e-05,
"loss": 3.7014,
"step": 563712
},
{
"epoch": 0.01,
"learning_rate": 4.076246934706881e-05,
"loss": 3.7149,
"step": 564224
},
{
"epoch": 0.01,
"learning_rate": 4.07540833995583e-05,
"loss": 3.6943,
"step": 564736
},
{
"epoch": 0.01,
"learning_rate": 4.074569745204778e-05,
"loss": 3.6954,
"step": 565248
},
{
"epoch": 0.01,
"learning_rate": 4.073731150453726e-05,
"loss": 3.6957,
"step": 565760
},
{
"epoch": 0.01,
"learning_rate": 4.072892555702674e-05,
"loss": 3.7013,
"step": 566272
},
{
"epoch": 0.01,
"learning_rate": 4.072053960951622e-05,
"loss": 3.7149,
"step": 566784
},
{
"epoch": 0.01,
"learning_rate": 4.07121536620057e-05,
"loss": 3.6974,
"step": 567296
},
{
"epoch": 0.01,
"learning_rate": 4.070376771449518e-05,
"loss": 3.6993,
"step": 567808
},
{
"epoch": 0.01,
"learning_rate": 4.069539814578839e-05,
"loss": 3.6882,
"step": 568320
},
{
"epoch": 0.01,
"learning_rate": 4.068701219827787e-05,
"loss": 3.7,
"step": 568832
},
{
"epoch": 0.01,
"learning_rate": 4.067864262957108e-05,
"loss": 3.6924,
"step": 569344
},
{
"epoch": 0.01,
"learning_rate": 4.067025668206056e-05,
"loss": 3.6977,
"step": 569856
},
{
"epoch": 0.01,
"learning_rate": 4.066187073455004e-05,
"loss": 3.7038,
"step": 570368
},
{
"epoch": 0.01,
"learning_rate": 4.065348478703952e-05,
"loss": 3.6969,
"step": 570880
},
{
"epoch": 0.01,
"learning_rate": 4.0645098839529e-05,
"loss": 3.6993,
"step": 571392
},
{
"epoch": 0.01,
"learning_rate": 4.063671289201848e-05,
"loss": 3.7123,
"step": 571904
},
{
"epoch": 0.01,
"learning_rate": 4.0628326944507964e-05,
"loss": 3.7026,
"step": 572416
},
{
"epoch": 0.01,
"learning_rate": 4.061995737580117e-05,
"loss": 3.7106,
"step": 572928
},
{
"epoch": 0.01,
"learning_rate": 4.061157142829065e-05,
"loss": 3.7037,
"step": 573440
},
{
"epoch": 0.01,
"learning_rate": 4.060318548078013e-05,
"loss": 3.6909,
"step": 573952
},
{
"epoch": 0.01,
"learning_rate": 4.059479953326961e-05,
"loss": 3.6953,
"step": 574464
},
{
"epoch": 0.01,
"learning_rate": 4.058642996456282e-05,
"loss": 3.7064,
"step": 574976
},
{
"epoch": 0.01,
"learning_rate": 4.05780440170523e-05,
"loss": 3.7034,
"step": 575488
},
{
"epoch": 0.01,
"learning_rate": 4.056965806954178e-05,
"loss": 3.6924,
"step": 576000
},
{
"epoch": 0.01,
"learning_rate": 4.056127212203126e-05,
"loss": 3.6827,
"step": 576512
},
{
"epoch": 0.01,
"learning_rate": 4.055288617452074e-05,
"loss": 3.6963,
"step": 577024
},
{
"epoch": 0.01,
"learning_rate": 4.054451660581395e-05,
"loss": 3.6842,
"step": 577536
},
{
"epoch": 0.01,
"learning_rate": 4.053613065830343e-05,
"loss": 3.6995,
"step": 578048
},
{
"epoch": 0.01,
"learning_rate": 4.052774471079292e-05,
"loss": 3.6943,
"step": 578560
},
{
"epoch": 0.01,
"learning_rate": 4.05193587632824e-05,
"loss": 3.7053,
"step": 579072
},
{
"epoch": 0.01,
"learning_rate": 4.051097281577188e-05,
"loss": 3.7024,
"step": 579584
},
{
"epoch": 0.02,
"learning_rate": 4.050258686826136e-05,
"loss": 3.6942,
"step": 580096
},
{
"epoch": 0.02,
"learning_rate": 4.049420092075083e-05,
"loss": 3.6897,
"step": 580608
},
{
"epoch": 0.02,
"learning_rate": 4.048581497324031e-05,
"loss": 3.6994,
"step": 581120
},
{
"epoch": 0.02,
"learning_rate": 4.0477445404533526e-05,
"loss": 3.6883,
"step": 581632
},
{
"epoch": 0.02,
"learning_rate": 4.0469075835826735e-05,
"loss": 3.6944,
"step": 582144
},
{
"epoch": 0.02,
"learning_rate": 4.0460689888316215e-05,
"loss": 3.6906,
"step": 582656
},
{
"epoch": 0.02,
"learning_rate": 4.0452303940805695e-05,
"loss": 3.7004,
"step": 583168
},
{
"epoch": 0.02,
"learning_rate": 4.0443917993295175e-05,
"loss": 3.6927,
"step": 583680
},
{
"epoch": 0.02,
"learning_rate": 4.0435532045784655e-05,
"loss": 3.7186,
"step": 584192
},
{
"epoch": 0.02,
"learning_rate": 4.042716247707787e-05,
"loss": 3.687,
"step": 584704
},
{
"epoch": 0.02,
"learning_rate": 4.041877652956735e-05,
"loss": 3.7052,
"step": 585216
},
{
"epoch": 0.02,
"learning_rate": 4.041039058205683e-05,
"loss": 3.701,
"step": 585728
},
{
"epoch": 0.02,
"learning_rate": 4.0402004634546304e-05,
"loss": 3.6919,
"step": 586240
},
{
"epoch": 0.02,
"learning_rate": 4.0393618687035784e-05,
"loss": 3.706,
"step": 586752
},
{
"epoch": 0.02,
"learning_rate": 4.0385232739525264e-05,
"loss": 3.6983,
"step": 587264
},
{
"epoch": 0.02,
"learning_rate": 4.037686317081848e-05,
"loss": 3.7039,
"step": 587776
},
{
"epoch": 0.02,
"learning_rate": 4.036847722330795e-05,
"loss": 3.6935,
"step": 588288
},
{
"epoch": 0.02,
"learning_rate": 4.036009127579743e-05,
"loss": 3.6884,
"step": 588800
},
{
"epoch": 0.02,
"learning_rate": 4.035170532828691e-05,
"loss": 3.6873,
"step": 589312
},
{
"epoch": 0.02,
"learning_rate": 4.034333575958012e-05,
"loss": 3.6987,
"step": 589824
},
{
"epoch": 0.02,
"learning_rate": 4.033494981206961e-05,
"loss": 3.6984,
"step": 590336
},
{
"epoch": 0.02,
"learning_rate": 4.032656386455909e-05,
"loss": 3.6879,
"step": 590848
},
{
"epoch": 0.02,
"learning_rate": 4.031817791704857e-05,
"loss": 3.6694,
"step": 591360
},
{
"epoch": 0.02,
"learning_rate": 4.030979196953805e-05,
"loss": 3.6922,
"step": 591872
},
{
"epoch": 0.02,
"learning_rate": 4.030142240083126e-05,
"loss": 3.7034,
"step": 592384
},
{
"epoch": 0.02,
"learning_rate": 4.029303645332074e-05,
"loss": 3.695,
"step": 592896
},
{
"epoch": 0.02,
"learning_rate": 4.028465050581022e-05,
"loss": 3.705,
"step": 593408
},
{
"epoch": 0.02,
"learning_rate": 4.02762645582997e-05,
"loss": 3.6963,
"step": 593920
},
{
"epoch": 0.02,
"learning_rate": 4.026787861078918e-05,
"loss": 3.6893,
"step": 594432
},
{
"epoch": 0.02,
"learning_rate": 4.025949266327866e-05,
"loss": 3.7023,
"step": 594944
},
{
"epoch": 0.02,
"learning_rate": 4.025112309457187e-05,
"loss": 3.6936,
"step": 595456
},
{
"epoch": 0.02,
"learning_rate": 4.024273714706135e-05,
"loss": 3.6871,
"step": 595968
},
{
"epoch": 0.02,
"learning_rate": 4.023435119955083e-05,
"loss": 3.6878,
"step": 596480
},
{
"epoch": 0.02,
"learning_rate": 4.0225965252040307e-05,
"loss": 3.6941,
"step": 596992
},
{
"epoch": 0.02,
"learning_rate": 4.021759568333352e-05,
"loss": 3.6895,
"step": 597504
},
{
"epoch": 0.02,
"learning_rate": 4.0209209735823e-05,
"loss": 3.686,
"step": 598016
},
{
"epoch": 0.02,
"learning_rate": 4.020082378831248e-05,
"loss": 3.6993,
"step": 598528
},
{
"epoch": 0.02,
"learning_rate": 4.019243784080196e-05,
"loss": 3.6896,
"step": 599040
},
{
"epoch": 0.02,
"learning_rate": 4.018405189329144e-05,
"loss": 3.6825,
"step": 599552
},
{
"epoch": 0.02,
"learning_rate": 4.017566594578092e-05,
"loss": 3.7035,
"step": 600064
},
{
"epoch": 0.02,
"learning_rate": 4.016729637707413e-05,
"loss": 3.6839,
"step": 600576
},
{
"epoch": 0.02,
"learning_rate": 4.015891042956361e-05,
"loss": 3.6993,
"step": 601088
},
{
"epoch": 0.02,
"learning_rate": 4.015052448205309e-05,
"loss": 3.7047,
"step": 601600
},
{
"epoch": 0.02,
"learning_rate": 4.014213853454257e-05,
"loss": 3.6948,
"step": 602112
},
{
"epoch": 0.02,
"learning_rate": 4.013375258703205e-05,
"loss": 3.6906,
"step": 602624
},
{
"epoch": 0.02,
"learning_rate": 4.012536663952153e-05,
"loss": 3.6926,
"step": 603136
},
{
"epoch": 0.02,
"learning_rate": 4.011698069201101e-05,
"loss": 3.6895,
"step": 603648
},
{
"epoch": 0.02,
"learning_rate": 4.010861112330423e-05,
"loss": 3.6896,
"step": 604160
},
{
"epoch": 0.02,
"learning_rate": 4.010022517579371e-05,
"loss": 3.707,
"step": 604672
},
{
"epoch": 0.02,
"learning_rate": 4.009183922828319e-05,
"loss": 3.7004,
"step": 605184
},
{
"epoch": 0.02,
"learning_rate": 4.008345328077267e-05,
"loss": 3.6983,
"step": 605696
},
{
"epoch": 0.02,
"learning_rate": 4.007506733326214e-05,
"loss": 3.6977,
"step": 606208
},
{
"epoch": 0.02,
"learning_rate": 4.0066697764555356e-05,
"loss": 3.688,
"step": 606720
},
{
"epoch": 0.02,
"learning_rate": 4.0058311817044836e-05,
"loss": 3.6967,
"step": 607232
},
{
"epoch": 0.02,
"learning_rate": 4.004992586953431e-05,
"loss": 3.6842,
"step": 607744
},
{
"epoch": 0.02,
"learning_rate": 4.004153992202379e-05,
"loss": 3.6856,
"step": 608256
},
{
"epoch": 0.02,
"learning_rate": 4.0033170353317005e-05,
"loss": 3.6958,
"step": 608768
},
{
"epoch": 0.02,
"learning_rate": 4.0024784405806485e-05,
"loss": 3.6896,
"step": 609280
},
{
"epoch": 0.02,
"learning_rate": 4.0016398458295965e-05,
"loss": 3.6774,
"step": 609792
},
{
"epoch": 0.02,
"learning_rate": 4.0008012510785445e-05,
"loss": 3.6946,
"step": 610304
},
{
"epoch": 0.03,
"eval_loss": 3.8578743934631348,
"eval_runtime": 569.8526,
"eval_samples_per_second": 669.631,
"eval_steps_per_second": 20.926,
"step": 610552
},
{
"epoch": 0.0,
"learning_rate": 3.999964294207866e-05,
"loss": 3.6948,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999125699456814e-05,
"loss": 3.6962,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.9982871047057614e-05,
"loss": 3.6946,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.9974485099547094e-05,
"loss": 3.6889,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996611553084031e-05,
"loss": 3.6875,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995772958332978e-05,
"loss": 3.6829,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994934363581926e-05,
"loss": 3.6909,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994095768830874e-05,
"loss": 3.6785,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993258811960196e-05,
"loss": 3.6814,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992420217209143e-05,
"loss": 3.6843,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991581622458092e-05,
"loss": 3.6944,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.99074302770704e-05,
"loss": 3.6766,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989904432955988e-05,
"loss": 3.6867,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.989067476085309e-05,
"loss": 3.6742,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.988228881334257e-05,
"loss": 3.6932,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.987390286583205e-05,
"loss": 3.6714,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986551691832153e-05,
"loss": 3.6755,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.985713097081101e-05,
"loss": 3.6811,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848761402104216e-05,
"loss": 3.6807,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.9840375454593696e-05,
"loss": 3.6873,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.9831989507083176e-05,
"loss": 3.6828,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.9823603559572656e-05,
"loss": 3.6995,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.9815217612062136e-05,
"loss": 3.6828,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980684804335535e-05,
"loss": 3.6864,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979846209584483e-05,
"loss": 3.681,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.979007614833431e-05,
"loss": 3.6861,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.978169020082379e-05,
"loss": 3.6869,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977330425331327e-05,
"loss": 3.6831,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976493468460648e-05,
"loss": 3.6833,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975654873709596e-05,
"loss": 3.684,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974816278958544e-05,
"loss": 3.6716,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973977684207492e-05,
"loss": 3.6868,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973140727336813e-05,
"loss": 3.694,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972302132585761e-05,
"loss": 3.6823,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971463537834709e-05,
"loss": 3.6783,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970624943083657e-05,
"loss": 3.6883,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.9697863483326056e-05,
"loss": 3.6779,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.9689477535815536e-05,
"loss": 3.6829,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.9681107967108746e-05,
"loss": 3.6835,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.9672722019598225e-05,
"loss": 3.6723,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.9664336072087705e-05,
"loss": 3.6728,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.9655950124577185e-05,
"loss": 3.6643,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.9647564177066665e-05,
"loss": 3.6893,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.9639194608359874e-05,
"loss": 3.6773,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9630808660849354e-05,
"loss": 3.6712,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.9622422713338834e-05,
"loss": 3.6831,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.9614036765828314e-05,
"loss": 3.6709,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.9605667197121523e-05,
"loss": 3.6876,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959728124961101e-05,
"loss": 3.6734,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958889530210049e-05,
"loss": 3.6769,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.958050935458997e-05,
"loss": 3.674,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957212340707945e-05,
"loss": 3.674,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956375383837266e-05,
"loss": 3.6813,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955536789086214e-05,
"loss": 3.6646,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954698194335162e-05,
"loss": 3.6759,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953859599584109e-05,
"loss": 3.6736,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.953021004833057e-05,
"loss": 3.6761,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952184047962379e-05,
"loss": 3.6751,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951345453211327e-05,
"loss": 3.6869,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950506858460275e-05,
"loss": 3.6637,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949668263709223e-05,
"loss": 3.671,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948829668958171e-05,
"loss": 3.6659,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.947992712087492e-05,
"loss": 3.6719,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.94715411733644e-05,
"loss": 3.6838,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946315522585388e-05,
"loss": 3.6713,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945476927834336e-05,
"loss": 3.6764,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.9446399709636566e-05,
"loss": 3.6543,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9438013762126046e-05,
"loss": 3.6771,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.9429627814615526e-05,
"loss": 3.6632,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.9421241867105006e-05,
"loss": 3.6675,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.9412872298398215e-05,
"loss": 3.6745,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.94044863508877e-05,
"loss": 3.6723,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939610040337718e-05,
"loss": 3.6696,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938771445586666e-05,
"loss": 3.6883,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937932850835614e-05,
"loss": 3.6719,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937095893964935e-05,
"loss": 3.6816,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936257299213883e-05,
"loss": 3.6783,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935418704462831e-05,
"loss": 3.6625,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934580109711779e-05,
"loss": 3.6616,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.9337431528411e-05,
"loss": 3.6769,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932904558090048e-05,
"loss": 3.6805,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.932065963338996e-05,
"loss": 3.6717,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.931227368587944e-05,
"loss": 3.6503,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930388773836892e-05,
"loss": 3.6644,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.9295518169662135e-05,
"loss": 3.6608,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.9287132222151615e-05,
"loss": 3.6699,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.9278746274641095e-05,
"loss": 3.6717,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.9270360327130575e-05,
"loss": 3.6763,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.9261974379620055e-05,
"loss": 3.6724,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.9253604810913264e-05,
"loss": 3.6649,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.9245218863402744e-05,
"loss": 3.6654,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.9236832915892224e-05,
"loss": 3.6668,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.9228446968381704e-05,
"loss": 3.6598,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.922007739967491e-05,
"loss": 3.673,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.921169145216439e-05,
"loss": 3.6646,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.920330550465387e-05,
"loss": 3.6703,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.919491955714335e-05,
"loss": 3.6656,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.918653360963283e-05,
"loss": 3.6872,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.917816404092605e-05,
"loss": 3.6623,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916977809341553e-05,
"loss": 3.6762,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916139214590501e-05,
"loss": 3.6749,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915300619839449e-05,
"loss": 3.6655,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914462025088397e-05,
"loss": 3.6746,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913625068217718e-05,
"loss": 3.6708,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912786473466666e-05,
"loss": 3.6757,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911947878715614e-05,
"loss": 3.6636,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911109283964562e-05,
"loss": 3.661,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.91027068921351e-05,
"loss": 3.6627,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909433732342831e-05,
"loss": 3.6692,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.9085951375917787e-05,
"loss": 3.6697,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907756542840727e-05,
"loss": 3.665,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906917948089675e-05,
"loss": 3.6423,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060793533386226e-05,
"loss": 3.6688,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905242396467944e-05,
"loss": 3.6713,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904403801716892e-05,
"loss": 3.6658,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.90356520696584e-05,
"loss": 3.6748,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9027266122147875e-05,
"loss": 3.6731,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.901889655344109e-05,
"loss": 3.6605,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.901051060593057e-05,
"loss": 3.6766,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900212465842005e-05,
"loss": 3.6665,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.8993738710909524e-05,
"loss": 3.6578,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898536914220274e-05,
"loss": 3.6617,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897698319469223e-05,
"loss": 3.6661,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.89685972471817e-05,
"loss": 3.6629,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.896021129967118e-05,
"loss": 3.6589,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.8951841730964396e-05,
"loss": 3.6696,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.8943455783453876e-05,
"loss": 3.6666,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.893506983594335e-05,
"loss": 3.6554,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.892668388843283e-05,
"loss": 3.673,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.891829794092231e-05,
"loss": 3.6567,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.890992837221552e-05,
"loss": 3.6731,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.8901542424705e-05,
"loss": 3.6817,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889315647719448e-05,
"loss": 3.6635,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.8884770529683965e-05,
"loss": 3.6652,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.8876400960977174e-05,
"loss": 3.6638,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.8868015013466654e-05,
"loss": 3.6617,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.8859629065956134e-05,
"loss": 3.6639,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.8851243118445614e-05,
"loss": 3.6788,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884287354973882e-05,
"loss": 3.6766,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.88344876022283e-05,
"loss": 3.6673,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882610165471778e-05,
"loss": 3.6684,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881771570720726e-05,
"loss": 3.6686,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880934613850047e-05,
"loss": 3.6639,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880096019098995e-05,
"loss": 3.6616,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879257424347943e-05,
"loss": 3.6587,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878418829596892e-05,
"loss": 3.6672,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877581872726213e-05,
"loss": 3.6635,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876743277975161e-05,
"loss": 3.6511,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875904683224109e-05,
"loss": 3.6653,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.855044364929199,
"eval_runtime": 318.203,
"eval_samples_per_second": 1199.206,
"eval_steps_per_second": 37.476,
"step": 686871
},
{
"epoch": 1.0,
"learning_rate": 3.875066088473057e-05,
"loss": 3.6617,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.8742291316023777e-05,
"loss": 3.6723,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.8733905368513256e-05,
"loss": 3.6687,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.8725519421002736e-05,
"loss": 3.6603,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8717133473492216e-05,
"loss": 3.6669,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.8708763904785425e-05,
"loss": 3.6599,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.8700377957274905e-05,
"loss": 3.659,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.8691992009764385e-05,
"loss": 3.6556,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.8683606062253865e-05,
"loss": 3.654,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.867523649354708e-05,
"loss": 3.6622,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.866685054603656e-05,
"loss": 3.665,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.865846459852604e-05,
"loss": 3.6509,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.865007865101552e-05,
"loss": 3.662,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.864170908230873e-05,
"loss": 3.6496,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.863332313479821e-05,
"loss": 3.6618,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.862493718728769e-05,
"loss": 3.6423,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.861655123977717e-05,
"loss": 3.6533,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.860816529226665e-05,
"loss": 3.6571,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.859979572355986e-05,
"loss": 3.6537,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859140977604934e-05,
"loss": 3.6675,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858302382853882e-05,
"loss": 3.6494,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.8574637881028306e-05,
"loss": 3.679,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.8566251933517786e-05,
"loss": 3.6546,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.8557882364810995e-05,
"loss": 3.6592,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.8549496417300475e-05,
"loss": 3.6576,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.8541110469789955e-05,
"loss": 3.6628,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.8532724522279435e-05,
"loss": 3.6615,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.8524354953572644e-05,
"loss": 3.6545,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.8515969006062124e-05,
"loss": 3.6571,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.8507583058551604e-05,
"loss": 3.6608,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.8499197111041084e-05,
"loss": 3.6402,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.849082754233429e-05,
"loss": 3.6629,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848244159482377e-05,
"loss": 3.666,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847405564731326e-05,
"loss": 3.6575,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846566969980274e-05,
"loss": 3.6511,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845730013109595e-05,
"loss": 3.6641,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.844891418358543e-05,
"loss": 3.656,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.844052823607491e-05,
"loss": 3.6578,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843214228856439e-05,
"loss": 3.6579,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.84237727198576e-05,
"loss": 3.6447,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841538677234708e-05,
"loss": 3.6481,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840700082483656e-05,
"loss": 3.6384,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839861487732604e-05,
"loss": 3.6624,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.839022892981552e-05,
"loss": 3.652,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.8381859361108726e-05,
"loss": 3.6434,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837347341359821e-05,
"loss": 3.6586,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836508746608769e-05,
"loss": 3.6465,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835670151857717e-05,
"loss": 3.6603,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834833194987038e-05,
"loss": 3.6553,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.833994600235986e-05,
"loss": 3.649,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833156005484934e-05,
"loss": 3.6496,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832317410733882e-05,
"loss": 3.6476,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.831480453863203e-05,
"loss": 3.6553,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.830641859112151e-05,
"loss": 3.6368,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829803264361099e-05,
"loss": 3.654,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828964669610047e-05,
"loss": 3.6448,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828127712739368e-05,
"loss": 3.6523,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827289117988317e-05,
"loss": 3.6463,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826450523237265e-05,
"loss": 3.6607,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825611928486213e-05,
"loss": 3.6469,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.8247749716155336e-05,
"loss": 3.6402,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.8239363768644816e-05,
"loss": 3.6475,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.8230977821134296e-05,
"loss": 3.6394,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.8222591873623776e-05,
"loss": 3.6569,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.821420592611325e-05,
"loss": 3.652,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8205836357406465e-05,
"loss": 3.6495,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8197450409895945e-05,
"loss": 3.6324,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.8189064462385425e-05,
"loss": 3.6501,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.8180678514874905e-05,
"loss": 3.6399,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817230894616812e-05,
"loss": 3.641,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.81639229986576e-05,
"loss": 3.6474,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.8155537051147074e-05,
"loss": 3.6461,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.8147151103636554e-05,
"loss": 3.646,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.8138765156126033e-05,
"loss": 3.663,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.813039558741925e-05,
"loss": 3.6494,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812200963990872e-05,
"loss": 3.6575,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.81136236923982e-05,
"loss": 3.6489,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810523774488768e-05,
"loss": 3.6418,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.80968681761809e-05,
"loss": 3.6377,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808848222867037e-05,
"loss": 3.6506,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.808009628115986e-05,
"loss": 3.6524,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807171033364934e-05,
"loss": 3.6523,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806334076494255e-05,
"loss": 3.6272,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805495481743203e-05,
"loss": 3.6375,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804656886992151e-05,
"loss": 3.6348,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.803818292241099e-05,
"loss": 3.6447,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.8029813353704196e-05,
"loss": 3.6433,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.8021427406193676e-05,
"loss": 3.6548,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.8013041458683156e-05,
"loss": 3.6488,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.8004655511172636e-05,
"loss": 3.6441,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.7996285942465845e-05,
"loss": 3.6397,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.7987899994955325e-05,
"loss": 3.6414,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797951404744481e-05,
"loss": 3.6345,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797112809993429e-05,
"loss": 3.6469,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.79627585312275e-05,
"loss": 3.6434,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795437258371698e-05,
"loss": 3.6418,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.794598663620646e-05,
"loss": 3.6444,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793760068869594e-05,
"loss": 3.6581,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792923111998915e-05,
"loss": 3.6412,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792084517247863e-05,
"loss": 3.6536,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791245922496811e-05,
"loss": 3.6489,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790407327745759e-05,
"loss": 3.645,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789568732994707e-05,
"loss": 3.6432,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788731776124028e-05,
"loss": 3.6506,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.7878931813729766e-05,
"loss": 3.6492,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.7870545866219246e-05,
"loss": 3.6398,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.7862159918708725e-05,
"loss": 3.6386,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.7853790350001935e-05,
"loss": 3.6348,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.7845404402491415e-05,
"loss": 3.6423,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.7837018454980894e-05,
"loss": 3.6483,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.7828632507470374e-05,
"loss": 3.6423,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.7820262938763584e-05,
"loss": 3.6219,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.7811876991253063e-05,
"loss": 3.6379,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.7803491043742543e-05,
"loss": 3.6453,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.7795105096232023e-05,
"loss": 3.646,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778673552752523e-05,
"loss": 3.6526,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777834958001471e-05,
"loss": 3.648,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.77699636325042e-05,
"loss": 3.6384,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776157768499368e-05,
"loss": 3.6476,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.775319173748316e-05,
"loss": 3.6452,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774482216877637e-05,
"loss": 3.6382,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773643622126585e-05,
"loss": 3.6342,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772805027375533e-05,
"loss": 3.6453,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771966432624481e-05,
"loss": 3.635,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771129475753802e-05,
"loss": 3.6395,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.77029088100275e-05,
"loss": 3.6433,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769452286251698e-05,
"loss": 3.6457,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.768613691500646e-05,
"loss": 3.6314,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767775096749594e-05,
"loss": 3.6465,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.766938139878915e-05,
"loss": 3.634,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766099545127863e-05,
"loss": 3.6499,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765260950376811e-05,
"loss": 3.6568,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.764422355625759e-05,
"loss": 3.6392,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.76358539875508e-05,
"loss": 3.6376,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.762746804004028e-05,
"loss": 3.6445,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761908209252976e-05,
"loss": 3.6376,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.761069614501924e-05,
"loss": 3.6409,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760232657631245e-05,
"loss": 3.6542,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759394062880193e-05,
"loss": 3.6482,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758555468129141e-05,
"loss": 3.6466,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.757716873378089e-05,
"loss": 3.6463,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.7568799165074107e-05,
"loss": 3.6469,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.7560413217563586e-05,
"loss": 3.6374,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.7552027270053066e-05,
"loss": 3.638,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.7543641322542546e-05,
"loss": 3.6351,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.7535271753835755e-05,
"loss": 3.6463,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.7526885806325235e-05,
"loss": 3.6404,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.7518499858814715e-05,
"loss": 3.6227,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.7510113911304195e-05,
"loss": 3.6444,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 3.8525781631469727,
"eval_runtime": 310.6369,
"eval_samples_per_second": 1228.415,
"eval_steps_per_second": 38.389,
"step": 763190
},
{
"epoch": 0.0,
"learning_rate": 3.7501744342597404e-05,
"loss": 3.6517,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.7493358395086884e-05,
"loss": 3.6382,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.7484972447576364e-05,
"loss": 3.6427,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.7476586500065844e-05,
"loss": 3.6504,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.746821693135906e-05,
"loss": 3.6575,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.745983098384854e-05,
"loss": 3.6463,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.745144503633802e-05,
"loss": 3.6475,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.74430590888275e-05,
"loss": 3.6364,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743468952012071e-05,
"loss": 3.6347,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742630357261019e-05,
"loss": 3.6422,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741791762509967e-05,
"loss": 3.6499,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740953167758915e-05,
"loss": 3.6393,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740114573007862e-05,
"loss": 3.6429,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739277616137184e-05,
"loss": 3.6289,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738439021386132e-05,
"loss": 3.6366,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.73760042663508e-05,
"loss": 3.6203,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736761831884028e-05,
"loss": 3.6376,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.7359248750133494e-05,
"loss": 3.6398,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.7350862802622974e-05,
"loss": 3.6294,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.7342476855112454e-05,
"loss": 3.652,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733409090760193e-05,
"loss": 3.6488,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.732572133889514e-05,
"loss": 3.6446,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731733539138462e-05,
"loss": 3.639,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.7308949443874096e-05,
"loss": 3.6373,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7300563496363576e-05,
"loss": 3.6456,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.729219392765679e-05,
"loss": 3.6496,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.728380798014627e-05,
"loss": 3.6274,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727542203263575e-05,
"loss": 3.6418,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726703608512523e-05,
"loss": 3.6331,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725866651641845e-05,
"loss": 3.634,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.725028056890793e-05,
"loss": 3.6398,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.72418946213974e-05,
"loss": 3.6415,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723350867388688e-05,
"loss": 3.6381,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.7225139105180096e-05,
"loss": 3.6539,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721675315766957e-05,
"loss": 3.6381,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720836721015905e-05,
"loss": 3.64,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.719998126264853e-05,
"loss": 3.6454,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719159531513801e-05,
"loss": 3.626,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718322574643122e-05,
"loss": 3.6306,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.7174839798920705e-05,
"loss": 3.6302,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.7166453851410185e-05,
"loss": 3.6248,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.7158067903899665e-05,
"loss": 3.6322,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.7149698335192874e-05,
"loss": 3.6456,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.7141312387682354e-05,
"loss": 3.6321,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.7132926440171834e-05,
"loss": 3.6345,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.7124540492661314e-05,
"loss": 3.6328,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711617092395452e-05,
"loss": 3.6374,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.7107784976444e-05,
"loss": 3.6235,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709939902893348e-05,
"loss": 3.6153,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709101308142296e-05,
"loss": 3.6417,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708264351271617e-05,
"loss": 3.6397,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707425756520566e-05,
"loss": 3.6472,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.706587161769514e-05,
"loss": 3.6354,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705748567018462e-05,
"loss": 3.6278,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.704911610147783e-05,
"loss": 3.6262,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.704073015396731e-05,
"loss": 3.6266,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703234420645679e-05,
"loss": 3.6457,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702395825894627e-05,
"loss": 3.6155,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.701558869023948e-05,
"loss": 3.6566,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.700720274272896e-05,
"loss": 3.6356,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699881679521844e-05,
"loss": 3.6102,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.699043084770792e-05,
"loss": 3.6418,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.6982061279001126e-05,
"loss": 3.6284,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.6973675331490606e-05,
"loss": 3.6156,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696528938398009e-05,
"loss": 3.6356,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695690343646957e-05,
"loss": 3.6392,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694853386776278e-05,
"loss": 3.6199,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.694014792025226e-05,
"loss": 3.6352,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693176197274174e-05,
"loss": 3.6111,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692337602523122e-05,
"loss": 3.6239,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691500645652443e-05,
"loss": 3.6319,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690662050901391e-05,
"loss": 3.6266,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689823456150339e-05,
"loss": 3.6326,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.688984861399287e-05,
"loss": 3.6259,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688147904528608e-05,
"loss": 3.6425,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.687309309777556e-05,
"loss": 3.6322,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.6864707150265046e-05,
"loss": 3.6386,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.6856321202754526e-05,
"loss": 3.6252,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.6847935255244006e-05,
"loss": 3.6204,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.6839565686537215e-05,
"loss": 3.6328,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.6831179739026695e-05,
"loss": 3.6303,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.6822793791516175e-05,
"loss": 3.6293,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.6814407844005655e-05,
"loss": 3.6358,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.6806038275298864e-05,
"loss": 3.619,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.6797652327788344e-05,
"loss": 3.6147,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.6789266380277824e-05,
"loss": 3.6272,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.6780880432767304e-05,
"loss": 3.6346,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677251086406051e-05,
"loss": 3.62,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676412491655e-05,
"loss": 3.6311,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675573896903948e-05,
"loss": 3.6265,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.674735302152896e-05,
"loss": 3.6226,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.673898345282217e-05,
"loss": 3.6179,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.673059750531165e-05,
"loss": 3.624,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672221155780113e-05,
"loss": 3.6392,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671382561029061e-05,
"loss": 3.6322,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670545604158382e-05,
"loss": 3.6319,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.66970700940733e-05,
"loss": 3.6213,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668868414656278e-05,
"loss": 3.619,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.668029819905226e-05,
"loss": 3.6264,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667192863034547e-05,
"loss": 3.6352,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.6663542682834954e-05,
"loss": 3.6313,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.6655156735324434e-05,
"loss": 3.6326,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.6646770787813914e-05,
"loss": 3.6245,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.663840121910712e-05,
"loss": 3.6245,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.66300152715966e-05,
"loss": 3.6297,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662162932408608e-05,
"loss": 3.6255,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661324337657556e-05,
"loss": 3.6168,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.660487380786877e-05,
"loss": 3.6293,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.659648786035825e-05,
"loss": 3.6244,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.658810191284773e-05,
"loss": 3.623,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.657971596533721e-05,
"loss": 3.6176,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.657133001782669e-05,
"loss": 3.6176,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656296044911991e-05,
"loss": 3.6273,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655457450160939e-05,
"loss": 3.6262,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654618855409887e-05,
"loss": 3.6268,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.653780260658835e-05,
"loss": 3.6343,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.6529433037881556e-05,
"loss": 3.6346,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.6521047090371036e-05,
"loss": 3.6293,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.6512661142860516e-05,
"loss": 3.6271,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.6504275195349996e-05,
"loss": 3.6179,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.6495905626643205e-05,
"loss": 3.6283,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.6487519679132685e-05,
"loss": 3.6228,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.6479133731622165e-05,
"loss": 3.6195,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.6470747784111645e-05,
"loss": 3.6191,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646237821540486e-05,
"loss": 3.6268,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.645399226789434e-05,
"loss": 3.626,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.644560632038382e-05,
"loss": 3.6222,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.64372203728733e-05,
"loss": 3.622,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642885080416651e-05,
"loss": 3.6207,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.642046485665599e-05,
"loss": 3.6285,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641207890914547e-05,
"loss": 3.6258,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640369296163495e-05,
"loss": 3.6363,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639532339292816e-05,
"loss": 3.6178,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638693744541764e-05,
"loss": 3.6224,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637855149790712e-05,
"loss": 3.6306,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.63701655503966e-05,
"loss": 3.6181,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.6361795981689815e-05,
"loss": 3.6273,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.6353410034179295e-05,
"loss": 3.6264,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.6345024086668775e-05,
"loss": 3.6291,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633663813915825e-05,
"loss": 3.6379,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.6328268570451464e-05,
"loss": 3.6267,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.6319882622940944e-05,
"loss": 3.6243,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631149667543042e-05,
"loss": 3.6294,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.63031107279199e-05,
"loss": 3.6204,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629474115921311e-05,
"loss": 3.6204,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628635521170259e-05,
"loss": 3.6221,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.6277969264192066e-05,
"loss": 3.6193,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626958331668155e-05,
"loss": 3.6202,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626121374797477e-05,
"loss": 3.6189,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.8472540378570557,
"eval_runtime": 304.628,
"eval_samples_per_second": 1252.646,
"eval_steps_per_second": 39.146,
"step": 839510
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 5.7274476209150054e+17,
"trial_name": null,
"trial_params": null
}