{
  "base": "unsloth/gpt-oss-20b-unsloth-bnb-4bit",
  "epochs": 2.0,
  "lr": 0.0002,
  "rank": 16,
  "n_train": 1201,
  "n_val": 48,
  "train_seconds": 5385,
  "train_loss": 0.05007273310314346,
  "eval": {
    "eval_loss": 0.035037748515605927,
    "eval_runtime": 110.0544,
    "eval_samples_per_second": 0.436,
    "eval_steps_per_second": 0.218,
    "epoch": 2.0
  },
  "log_history": [
    {
      "loss": 0.23318450450897216,
      "grad_norm": 1.5675679445266724,
      "learning_rate": 5e-05,
      "epoch": 0.033277870216306155,
      "step": 5
    },
    {
      "loss": 0.09800589680671692,
      "grad_norm": 1.0014837980270386,
      "learning_rate": 0.00011250000000000001,
      "epoch": 0.06655574043261231,
      "step": 10
    },
    {
      "loss": 0.06956685185432435,
      "grad_norm": 0.5591109395027161,
      "learning_rate": 0.000175,
      "epoch": 0.09983361064891846,
      "step": 15
    },
    {
      "loss": 0.06257834434509277,
      "grad_norm": 0.43907880783081055,
      "learning_rate": 0.00019994570736865406,
      "epoch": 0.13311148086522462,
      "step": 20
    },
    {
      "loss": 0.05633952021598816,
      "grad_norm": 0.6507183313369751,
      "learning_rate": 0.00019961413253717213,
      "epoch": 0.16638935108153077,
      "step": 25
    },
    {
      "loss": 0.05565650463104248,
      "grad_norm": 0.46881163120269775,
      "learning_rate": 0.0001989821441880933,
      "epoch": 0.19966722129783693,
      "step": 30
    },
    {
      "loss": 0.06170967221260071,
      "grad_norm": 0.3107876181602478,
      "learning_rate": 0.0001980516482542224,
      "epoch": 0.23294509151414308,
      "step": 35
    },
    {
      "loss": 0.06616556644439697,
      "grad_norm": 0.3977068066596985,
      "learning_rate": 0.00019682545089919784,
      "epoch": 0.26622296173044924,
      "step": 40
    },
    {
      "loss": 0.05503295063972473,
      "grad_norm": 0.3961268961429596,
      "learning_rate": 0.00019530725005474195,
      "epoch": 0.2995008319467554,
      "step": 45
    },
    {
      "loss": 0.04668510556221008,
      "grad_norm": 0.5407523512840271,
      "learning_rate": 0.0001935016242685415,
      "epoch": 0.33277870216306155,
      "step": 50
    },
    {
      "loss": 0.06434003710746765,
      "grad_norm": 0.3896896541118622,
      "learning_rate": 0.0001914140188963917,
      "epoch": 0.36605657237936773,
      "step": 55
    },
    {
      "loss": 0.05060199499130249,
      "grad_norm": 0.47498011589050293,
      "learning_rate": 0.00018905072968024425,
      "epoch": 0.39933444259567386,
      "step": 60
    },
    {
      "loss": 0.05920557975769043,
      "grad_norm": 0.5028626918792725,
      "learning_rate": 0.00018641888376168484,
      "epoch": 0.43261231281198004,
      "step": 65
    },
    {
      "loss": 0.05897412300109863,
      "grad_norm": 0.27249830961227417,
      "learning_rate": 0.00018352641818809848,
      "epoch": 0.46589018302828616,
      "step": 70
    },
    {
      "loss": 0.060563582181930545,
      "grad_norm": 0.2820088267326355,
      "learning_rate": 0.00018038205597634393,
      "epoch": 0.49916805324459235,
      "step": 75
    },
    {
      "eval_loss": 0.04855774715542793,
      "eval_runtime": 109.1031,
      "eval_samples_per_second": 0.44,
      "eval_steps_per_second": 0.22,
      "epoch": 0.49916805324459235,
      "step": 75
    },
    {
      "loss": 0.053474980592727664,
      "grad_norm": 0.26608899235725403,
      "learning_rate": 0.00017699527980612304,
      "epoch": 0.5324459234608985,
      "step": 80
    },
    {
      "loss": 0.05269782543182373,
      "grad_norm": 0.47424036264419556,
      "learning_rate": 0.00017337630342238042,
      "epoch": 0.5657237936772047,
      "step": 85
    },
    {
      "loss": 0.04431299567222595,
      "grad_norm": 0.2915017902851105,
      "learning_rate": 0.00016953604083297665,
      "epoch": 0.5990016638935108,
      "step": 90
    },
    {
      "loss": 0.059468144178390504,
      "grad_norm": 0.44232964515686035,
      "learning_rate": 0.00016548607339452853,
      "epoch": 0.632279534109817,
      "step": 95
    },
    {
      "loss": 0.04879138767719269,
      "grad_norm": 0.3917384743690491,
      "learning_rate": 0.0001612386148856771,
      "epoch": 0.6655574043261231,
      "step": 100
    },
    {
      "loss": 0.053298580646514895,
      "grad_norm": 0.34147557616233826,
      "learning_rate": 0.00015680647467311557,
      "epoch": 0.6988352745424293,
      "step": 105
    },
    {
      "loss": 0.06263553500175476,
      "grad_norm": 0.3751288950443268,
      "learning_rate": 0.00015220301908145905,
      "epoch": 0.7321131447587355,
      "step": 110
    },
    {
      "loss": 0.046320125460624695,
      "grad_norm": 0.2635810971260071,
      "learning_rate": 0.00014744213108345604,
      "epoch": 0.7653910149750416,
      "step": 115
    },
    {
      "loss": 0.05368142127990723,
      "grad_norm": 0.5102227330207825,
      "learning_rate": 0.0001425381684321075,
      "epoch": 0.7986688851913477,
      "step": 120
    },
    {
      "loss": 0.04990728497505188,
      "grad_norm": 0.28165382146835327,
      "learning_rate": 0.0001375059203609562,
      "epoch": 0.831946755407654,
      "step": 125
    },
    {
      "loss": 0.047086745500564575,
      "grad_norm": 0.3740539848804474,
      "learning_rate": 0.00013236056298312958,
      "epoch": 0.8652246256239601,
      "step": 130
    },
    {
      "loss": 0.05073004364967346,
      "grad_norm": 0.24512438476085663,
      "learning_rate": 0.00012711761352364172,
      "epoch": 0.8985024958402662,
      "step": 135
    },
    {
      "loss": 0.04626903533935547,
      "grad_norm": 0.23963695764541626,
      "learning_rate": 0.00012179288352297984,
      "epoch": 0.9317803660565723,
      "step": 140
    },
    {
      "loss": 0.0459677129983902,
      "grad_norm": 0.2949606478214264,
      "learning_rate": 0.00011640243115310218,
      "epoch": 0.9650582362728786,
      "step": 145
    },
    {
      "loss": 0.056029146909713744,
      "grad_norm": 0.16958178579807281,
      "learning_rate": 0.00011096251278965172,
      "epoch": 0.9983361064891847,
      "step": 150
    },
    {
      "eval_loss": 0.03915443643927574,
      "eval_runtime": 106.7046,
      "eval_samples_per_second": 0.45,
      "eval_steps_per_second": 0.225,
      "epoch": 0.9983361064891847,
      "step": 150
    },
    {
      "loss": 0.04040303230285645,
      "grad_norm": 0.18060733377933502,
      "learning_rate": 0.00010548953398643275,
      "epoch": 1.026622296173045,
      "step": 155
    },
    {
      "loss": 0.04127705693244934,
      "grad_norm": 0.22245723009109497,
      "learning_rate": 0.0001,
      "epoch": 1.059900166389351,
      "step": 160
    },
    {
      "loss": 0.04128023087978363,
      "grad_norm": 0.20679683983325958,
      "learning_rate": 9.451046601356725e-05,
      "epoch": 1.0931780366056572,
      "step": 165
    },
    {
      "loss": 0.04075656235218048,
      "grad_norm": 0.2824983298778534,
      "learning_rate": 8.903748721034827e-05,
      "epoch": 1.1264559068219633,
      "step": 170
    },
    {
      "loss": 0.032700645923614505,
      "grad_norm": 0.1779838353395462,
      "learning_rate": 8.359756884689784e-05,
      "epoch": 1.1597337770382696,
      "step": 175
    },
    {
      "loss": 0.0488627552986145,
      "grad_norm": 0.41342025995254517,
      "learning_rate": 7.820711647702017e-05,
      "epoch": 1.1930116472545758,
      "step": 180
    },
    {
      "loss": 0.039889439940452576,
      "grad_norm": 0.17202401161193848,
      "learning_rate": 7.28823864763583e-05,
      "epoch": 1.2262895174708819,
      "step": 185
    },
    {
      "loss": 0.04121506214141846,
      "grad_norm": 0.2019381821155548,
      "learning_rate": 6.763943701687045e-05,
      "epoch": 1.259567387687188,
      "step": 190
    },
    {
      "loss": 0.03708588480949402,
      "grad_norm": 0.18151353299617767,
      "learning_rate": 6.249407963904382e-05,
      "epoch": 1.2928452579034941,
      "step": 195
    },
    {
      "loss": 0.03387935757637024,
      "grad_norm": 0.16017630696296692,
      "learning_rate": 5.746183156789252e-05,
      "epoch": 1.3261231281198003,
      "step": 200
    },
    {
      "loss": 0.03551802933216095,
      "grad_norm": 0.160872682929039,
      "learning_rate": 5.2557868916543994e-05,
      "epoch": 1.3594009983361066,
      "step": 205
    },
    {
      "loss": 0.03997071981430054,
      "grad_norm": 0.25131309032440186,
      "learning_rate": 4.779698091854098e-05,
      "epoch": 1.3926788685524127,
      "step": 210
    },
    {
      "loss": 0.04206432700157166,
      "grad_norm": 0.18861962854862213,
      "learning_rate": 4.3193525326884435e-05,
      "epoch": 1.4259567387687189,
      "step": 215
    },
    {
      "loss": 0.03841230273246765,
      "grad_norm": 0.2180393636226654,
      "learning_rate": 3.87613851143229e-05,
      "epoch": 1.459234608985025,
      "step": 220
    },
    {
      "loss": 0.03855002522468567,
      "grad_norm": 0.285129189491272,
      "learning_rate": 3.45139266054715e-05,
      "epoch": 1.4925124792013311,
      "step": 225
    },
    {
      "eval_loss": 0.036705683916807175,
      "eval_runtime": 107.4042,
      "eval_samples_per_second": 0.447,
      "eval_steps_per_second": 0.223,
      "epoch": 1.4925124792013311,
      "step": 225
    },
    {
      "loss": 0.04107905328273773,
      "grad_norm": 0.3099617660045624,
      "learning_rate": 3.0463959167023336e-05,
      "epoch": 1.5257903494176372,
      "step": 230
    },
    {
      "loss": 0.034897661209106444,
      "grad_norm": 0.18056237697601318,
      "learning_rate": 2.6623696577619627e-05,
      "epoch": 1.5590682196339434,
      "step": 235
    },
    {
      "loss": 0.040480229258537295,
      "grad_norm": 0.16304191946983337,
      "learning_rate": 2.3004720193876973e-05,
      "epoch": 1.5923460898502495,
      "step": 240
    },
    {
      "loss": 0.041963180899620055,
      "grad_norm": 0.20544564723968506,
      "learning_rate": 1.961794402365611e-05,
      "epoch": 1.6256239600665556,
      "step": 245
    },
    {
      "loss": 0.04076297581195831,
      "grad_norm": 0.1998342126607895,
      "learning_rate": 1.647358181190153e-05,
      "epoch": 1.6589018302828618,
      "step": 250
    },
    {
      "loss": 0.03765386044979095,
      "grad_norm": 0.29265111684799194,
      "learning_rate": 1.3581116238315195e-05,
      "epoch": 1.692179700499168,
      "step": 255
    },
    {
      "loss": 0.03905968368053436,
      "grad_norm": 0.3158849775791168,
      "learning_rate": 1.0949270319755766e-05,
      "epoch": 1.7254575707154742,
      "step": 260
    },
    {
      "loss": 0.03416600227355957,
      "grad_norm": 0.20490851998329163,
      "learning_rate": 8.585981103608342e-06,
      "epoch": 1.7587354409317804,
      "step": 265
    },
    {
      "loss": 0.03573819100856781,
      "grad_norm": 0.14396147429943085,
      "learning_rate": 6.498375731458528e-06,
      "epoch": 1.7920133111480865,
      "step": 270
    },
    {
      "loss": 0.0350035548210144,
      "grad_norm": 0.2610838711261749,
      "learning_rate": 4.692749945258057e-06,
      "epoch": 1.8252911813643928,
      "step": 275
    },
    {
      "loss": 0.02864158749580383,
      "grad_norm": 0.1647801697254181,
      "learning_rate": 3.1745491008021598e-06,
      "epoch": 1.858569051580699,
      "step": 280
    },
    {
      "loss": 0.03647815883159637,
      "grad_norm": 0.19215065240859985,
      "learning_rate": 1.9483517457776436e-06,
      "epoch": 1.891846921797005,
      "step": 285
    },
    {
      "loss": 0.037104851007461546,
      "grad_norm": 0.18784989416599274,
      "learning_rate": 1.0178558119067315e-06,
      "epoch": 1.9251247920133112,
      "step": 290
    },
    {
      "loss": 0.03571946620941162,
      "grad_norm": 0.16310757398605347,
      "learning_rate": 3.8586746282788244e-07,
      "epoch": 1.9584026622296173,
      "step": 295
    },
    {
      "loss": 0.03239317238330841,
      "grad_norm": 0.12636224925518036,
      "learning_rate": 5.4292631345942424e-08,
      "epoch": 1.9916805324459235,
      "step": 300
    },
    {
      "eval_loss": 0.03523457422852516,
      "eval_runtime": 107.1762,
      "eval_samples_per_second": 0.448,
      "eval_steps_per_second": 0.224,
      "epoch": 1.9916805324459235,
      "step": 300
    },
    {
      "eval_loss": 0.03514386713504791,
      "eval_runtime": 108.323,
      "eval_samples_per_second": 0.443,
      "eval_steps_per_second": 0.222,
      "epoch": 2.0,
      "step": 302
    },
    {
      "train_runtime": 5377.3211,
      "train_samples_per_second": 0.447,
      "train_steps_per_second": 0.056,
      "total_flos": 4.1742372787113254e+17,
      "train_loss": 0.05007273310314346,
      "epoch": 2.0,
      "step": 302
    },
    {
      "eval_loss": 0.035037748515605927,
      "eval_runtime": 110.0544,
      "eval_samples_per_second": 0.436,
      "eval_steps_per_second": 0.218,
      "epoch": 2.0,
      "step": 302
    }
  ]
}