Files
ModelHub XC 93d8953072 初始化项目,由ModelHub XC社区提供模型
Model: CLMBR/old-rel-cl-transformer-1
Source: Original Platform
2026-07-02 23:35:23 +08:00

2732 lines
55 KiB
JSON

{
"best_metric": 3.9574086666107178,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/1/checkpoints/checkpoint-228957",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 228957,
"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
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.561882739966116e+17,
"trial_name": null,
"trial_params": null
}