{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 309,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04854368932038835,
      "grad_norm": 5.743930339813232,
      "learning_rate": 5e-05,
      "loss": 1.068207359313965,
      "step": 5
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": 1.8176714181900024,
      "learning_rate": 0.00011250000000000001,
      "loss": 0.542995548248291,
      "step": 10
    },
    {
      "epoch": 0.14563106796116504,
      "grad_norm": 1.1854413747787476,
      "learning_rate": 0.000175,
      "loss": 0.31736025810241697,
      "step": 15
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.794679582118988,
      "learning_rate": 0.00019795221843003414,
      "loss": 0.21744627952575685,
      "step": 20
    },
    {
      "epoch": 0.24271844660194175,
      "grad_norm": 0.9740322232246399,
      "learning_rate": 0.0001945392491467577,
      "loss": 0.15123528242111206,
      "step": 25
    },
    {
      "epoch": 0.2912621359223301,
      "grad_norm": 0.7435612678527832,
      "learning_rate": 0.00019112627986348125,
      "loss": 0.14309574365615846,
      "step": 30
    },
    {
      "epoch": 0.33980582524271846,
      "grad_norm": 1.5412979125976562,
      "learning_rate": 0.00018771331058020478,
      "loss": 0.16383438110351561,
      "step": 35
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 1.628558874130249,
      "learning_rate": 0.00018430034129692833,
      "loss": 0.10026392936706544,
      "step": 40
    },
    {
      "epoch": 0.4368932038834951,
      "grad_norm": 0.8788347840309143,
      "learning_rate": 0.0001808873720136519,
      "loss": 0.07897814512252807,
      "step": 45
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 1.105530023574829,
      "learning_rate": 0.00017747440273037544,
      "loss": 0.07873730063438415,
      "step": 50
    },
    {
      "epoch": 0.5339805825242718,
      "grad_norm": 0.4164130687713623,
      "learning_rate": 0.00017406143344709897,
      "loss": 0.061830222606658936,
      "step": 55
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 1.1068264245986938,
      "learning_rate": 0.00017064846416382255,
      "loss": 0.08510450124740601,
      "step": 60
    },
    {
      "epoch": 0.6310679611650486,
      "grad_norm": 0.5336887836456299,
      "learning_rate": 0.00016723549488054608,
      "loss": 0.059296411275863645,
      "step": 65
    },
    {
      "epoch": 0.6796116504854369,
      "grad_norm": 0.639773964881897,
      "learning_rate": 0.00016382252559726964,
      "loss": 0.051507222652435306,
      "step": 70
    },
    {
      "epoch": 0.7281553398058253,
      "grad_norm": 0.5094393491744995,
      "learning_rate": 0.0001604095563139932,
      "loss": 0.0535398006439209,
      "step": 75
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 1.305483102798462,
      "learning_rate": 0.00015699658703071675,
      "loss": 0.04520266652107239,
      "step": 80
    },
    {
      "epoch": 0.8252427184466019,
      "grad_norm": 0.5654668807983398,
      "learning_rate": 0.00015358361774744027,
      "loss": 0.045658618211746216,
      "step": 85
    },
    {
      "epoch": 0.8737864077669902,
      "grad_norm": 0.728904664516449,
      "learning_rate": 0.00015017064846416383,
      "loss": 0.042400938272476194,
      "step": 90
    },
    {
      "epoch": 0.9223300970873787,
      "grad_norm": 0.3077709376811981,
      "learning_rate": 0.00014675767918088738,
      "loss": 0.03792175054550171,
      "step": 95
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.9077224135398865,
      "learning_rate": 0.00014334470989761094,
      "loss": 0.04246949851512909,
      "step": 100
    },
    {
      "epoch": 1.0194174757281553,
      "grad_norm": 1.495755910873413,
      "learning_rate": 0.00013993174061433447,
      "loss": 0.027642276883125306,
      "step": 105
    },
    {
      "epoch": 1.0679611650485437,
      "grad_norm": 3.1497764587402344,
      "learning_rate": 0.00013651877133105805,
      "loss": 0.03732385635375977,
      "step": 110
    },
    {
      "epoch": 1.116504854368932,
      "grad_norm": 0.9969474077224731,
      "learning_rate": 0.00013310580204778158,
      "loss": 0.0499280720949173,
      "step": 115
    },
    {
      "epoch": 1.1650485436893203,
      "grad_norm": 1.5082579851150513,
      "learning_rate": 0.00012969283276450513,
      "loss": 0.05375739336013794,
      "step": 120
    },
    {
      "epoch": 1.2135922330097086,
      "grad_norm": 1.5173441171646118,
      "learning_rate": 0.00012627986348122866,
      "loss": 0.03192383646965027,
      "step": 125
    },
    {
      "epoch": 1.262135922330097,
      "grad_norm": 2.9910647869110107,
      "learning_rate": 0.00012286689419795224,
      "loss": 0.06204846501350403,
      "step": 130
    },
    {
      "epoch": 1.3106796116504853,
      "grad_norm": 2.186009407043457,
      "learning_rate": 0.00011945392491467577,
      "loss": 0.03155330121517182,
      "step": 135
    },
    {
      "epoch": 1.3592233009708738,
      "grad_norm": 0.9750834107398987,
      "learning_rate": 0.00011604095563139932,
      "loss": 0.036894726753234866,
      "step": 140
    },
    {
      "epoch": 1.4077669902912622,
      "grad_norm": 0.40808287262916565,
      "learning_rate": 0.00011262798634812288,
      "loss": 0.03167285621166229,
      "step": 145
    },
    {
      "epoch": 1.4563106796116505,
      "grad_norm": 0.6957395076751709,
      "learning_rate": 0.00010921501706484642,
      "loss": 0.028990346193313598,
      "step": 150
    },
    {
      "epoch": 1.5048543689320388,
      "grad_norm": 0.7266637086868286,
      "learning_rate": 0.00010580204778156998,
      "loss": 0.03194972574710846,
      "step": 155
    },
    {
      "epoch": 1.5533980582524272,
      "grad_norm": 0.8215630650520325,
      "learning_rate": 0.00010238907849829352,
      "loss": 0.026474198698997496,
      "step": 160
    },
    {
      "epoch": 1.6019417475728155,
      "grad_norm": 0.525887668132782,
      "learning_rate": 9.897610921501707e-05,
      "loss": 0.030842745304107667,
      "step": 165
    },
    {
      "epoch": 1.650485436893204,
      "grad_norm": 0.6405989527702332,
      "learning_rate": 9.556313993174063e-05,
      "loss": 0.02945426106452942,
      "step": 170
    },
    {
      "epoch": 1.6990291262135924,
      "grad_norm": 0.687443733215332,
      "learning_rate": 9.215017064846417e-05,
      "loss": 0.027361923456192018,
      "step": 175
    },
    {
      "epoch": 1.7475728155339807,
      "grad_norm": 0.9356411695480347,
      "learning_rate": 8.873720136518772e-05,
      "loss": 0.02166469246149063,
      "step": 180
    },
    {
      "epoch": 1.796116504854369,
      "grad_norm": 0.34714531898498535,
      "learning_rate": 8.532423208191128e-05,
      "loss": 0.023515135049819946,
      "step": 185
    },
    {
      "epoch": 1.8446601941747574,
      "grad_norm": 1.1613726615905762,
      "learning_rate": 8.191126279863482e-05,
      "loss": 0.03655298948287964,
      "step": 190
    },
    {
      "epoch": 1.8932038834951457,
      "grad_norm": 0.6787657141685486,
      "learning_rate": 7.849829351535837e-05,
      "loss": 0.029764598608016966,
      "step": 195
    },
    {
      "epoch": 1.941747572815534,
      "grad_norm": 0.7119050025939941,
      "learning_rate": 7.508532423208191e-05,
      "loss": 0.01837872862815857,
      "step": 200
    },
    {
      "epoch": 1.9902912621359223,
      "grad_norm": 0.4616338610649109,
      "learning_rate": 7.167235494880547e-05,
      "loss": 0.01884647011756897,
      "step": 205
    },
    {
      "epoch": 2.0388349514563107,
      "grad_norm": 1.1989543437957764,
      "learning_rate": 6.825938566552902e-05,
      "loss": 0.021225303411483765,
      "step": 210
    },
    {
      "epoch": 2.087378640776699,
      "grad_norm": 0.41152718663215637,
      "learning_rate": 6.484641638225257e-05,
      "loss": 0.018019913136959075,
      "step": 215
    },
    {
      "epoch": 2.1359223300970873,
      "grad_norm": 0.5726111531257629,
      "learning_rate": 6.143344709897612e-05,
      "loss": 0.019997699558734892,
      "step": 220
    },
    {
      "epoch": 2.1844660194174756,
      "grad_norm": 0.35450392961502075,
      "learning_rate": 5.802047781569966e-05,
      "loss": 0.022833940386772156,
      "step": 225
    },
    {
      "epoch": 2.233009708737864,
      "grad_norm": 0.5156122446060181,
      "learning_rate": 5.460750853242321e-05,
      "loss": 0.016732443869113923,
      "step": 230
    },
    {
      "epoch": 2.2815533980582523,
      "grad_norm": 0.2936283051967621,
      "learning_rate": 5.119453924914676e-05,
      "loss": 0.01689387857913971,
      "step": 235
    },
    {
      "epoch": 2.3300970873786406,
      "grad_norm": 0.685085117816925,
      "learning_rate": 4.778156996587031e-05,
      "loss": 0.014879977703094483,
      "step": 240
    },
    {
      "epoch": 2.378640776699029,
      "grad_norm": 0.627520740032196,
      "learning_rate": 4.436860068259386e-05,
      "loss": 0.016331207752227784,
      "step": 245
    },
    {
      "epoch": 2.4271844660194173,
      "grad_norm": 0.34707480669021606,
      "learning_rate": 4.095563139931741e-05,
      "loss": 0.018924489617347717,
      "step": 250
    },
    {
      "epoch": 2.475728155339806,
      "grad_norm": 0.34278836846351624,
      "learning_rate": 3.754266211604096e-05,
      "loss": 0.01643313020467758,
      "step": 255
    },
    {
      "epoch": 2.524271844660194,
      "grad_norm": 0.7122762799263,
      "learning_rate": 3.412969283276451e-05,
      "loss": 0.026705330610275267,
      "step": 260
    },
    {
      "epoch": 2.5728155339805827,
      "grad_norm": 0.4575437605381012,
      "learning_rate": 3.071672354948806e-05,
      "loss": 0.015714159607887267,
      "step": 265
    },
    {
      "epoch": 2.6213592233009706,
      "grad_norm": 0.411961168050766,
      "learning_rate": 2.7303754266211605e-05,
      "loss": 0.016397938132286072,
      "step": 270
    },
    {
      "epoch": 2.6699029126213594,
      "grad_norm": 0.5097138285636902,
      "learning_rate": 2.3890784982935157e-05,
      "loss": 0.025263005495071413,
      "step": 275
    },
    {
      "epoch": 2.7184466019417477,
      "grad_norm": 0.5515726208686829,
      "learning_rate": 2.0477815699658705e-05,
      "loss": 0.014341163635253906,
      "step": 280
    },
    {
      "epoch": 2.766990291262136,
      "grad_norm": 0.7219721078872681,
      "learning_rate": 1.7064846416382256e-05,
      "loss": 0.025267311930656434,
      "step": 285
    },
    {
      "epoch": 2.8155339805825244,
      "grad_norm": 0.3334020972251892,
      "learning_rate": 1.3651877133105803e-05,
      "loss": 0.01676362156867981,
      "step": 290
    },
    {
      "epoch": 2.8640776699029127,
      "grad_norm": 0.3331213891506195,
      "learning_rate": 1.0238907849829352e-05,
      "loss": 0.016262842714786528,
      "step": 295
    },
    {
      "epoch": 2.912621359223301,
      "grad_norm": 0.3939487338066101,
      "learning_rate": 6.825938566552901e-06,
      "loss": 0.02069661468267441,
      "step": 300
    },
    {
      "epoch": 2.9611650485436893,
      "grad_norm": 0.2489783763885498,
      "learning_rate": 3.4129692832764506e-06,
      "loss": 0.030664995312690735,
      "step": 305
    }
  ],
  "logging_steps": 5,
  "max_steps": 309,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5980007589169152.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}