{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7155635062611807,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011926058437686345,
      "grad_norm": 0.5661849975585938,
      "learning_rate": 4.999804802810596e-05,
      "loss": 1.4421,
      "step": 5
    },
    {
      "epoch": 0.02385211687537269,
      "grad_norm": 0.5908129811286926,
      "learning_rate": 4.999219241723937e-05,
      "loss": 1.3306,
      "step": 10
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 0.6965810060501099,
      "learning_rate": 4.998243408179925e-05,
      "loss": 1.1873,
      "step": 15
    },
    {
      "epoch": 0.04770423375074538,
      "grad_norm": 0.5752276182174683,
      "learning_rate": 4.9968774545625344e-05,
      "loss": 1.0583,
      "step": 20
    },
    {
      "epoch": 0.05963029218843172,
      "grad_norm": 0.6488135457038879,
      "learning_rate": 4.9951215941760075e-05,
      "loss": 1.0045,
      "step": 25
    },
    {
      "epoch": 0.07155635062611806,
      "grad_norm": 0.7977299094200134,
      "learning_rate": 4.992976101211558e-05,
      "loss": 0.9836,
      "step": 30
    },
    {
      "epoch": 0.08348240906380441,
      "grad_norm": 0.8842712044715881,
      "learning_rate": 4.99044131070454e-05,
      "loss": 0.8925,
      "step": 35
    },
    {
      "epoch": 0.09540846750149076,
      "grad_norm": 0.798170804977417,
      "learning_rate": 4.987517618482142e-05,
      "loss": 0.8783,
      "step": 40
    },
    {
      "epoch": 0.1073345259391771,
      "grad_norm": 0.8196467757225037,
      "learning_rate": 4.984205481101565e-05,
      "loss": 0.8681,
      "step": 45
    },
    {
      "epoch": 0.11926058437686345,
      "grad_norm": 0.9973539113998413,
      "learning_rate": 4.980505415778738e-05,
      "loss": 0.8251,
      "step": 50
    },
    {
      "epoch": 0.13118664281454978,
      "grad_norm": 0.8836011290550232,
      "learning_rate": 4.97641800030754e-05,
      "loss": 0.8079,
      "step": 55
    },
    {
      "epoch": 0.14311270125223613,
      "grad_norm": 0.9255298972129822,
      "learning_rate": 4.971943872969582e-05,
      "loss": 0.7769,
      "step": 60
    },
    {
      "epoch": 0.15503875968992248,
      "grad_norm": 0.9712087512016296,
      "learning_rate": 4.967083732434529e-05,
      "loss": 0.777,
      "step": 65
    },
    {
      "epoch": 0.16696481812760883,
      "grad_norm": 0.7609415054321289,
      "learning_rate": 4.961838337650997e-05,
      "loss": 0.7303,
      "step": 70
    },
    {
      "epoch": 0.17889087656529518,
      "grad_norm": 0.8297658562660217,
      "learning_rate": 4.9562085077280443e-05,
      "loss": 0.7442,
      "step": 75
    },
    {
      "epoch": 0.19081693500298152,
      "grad_norm": 1.01498281955719,
      "learning_rate": 4.950195121807251e-05,
      "loss": 0.7077,
      "step": 80
    },
    {
      "epoch": 0.20274299344066785,
      "grad_norm": 0.9629709720611572,
      "learning_rate": 4.943799118925443e-05,
      "loss": 0.673,
      "step": 85
    },
    {
      "epoch": 0.2146690518783542,
      "grad_norm": 0.9121557474136353,
      "learning_rate": 4.937021497868047e-05,
      "loss": 0.7109,
      "step": 90
    },
    {
      "epoch": 0.22659511031604054,
      "grad_norm": 0.841573178768158,
      "learning_rate": 4.9298633170131304e-05,
      "loss": 0.6798,
      "step": 95
    },
    {
      "epoch": 0.2385211687537269,
      "grad_norm": 0.9693652391433716,
      "learning_rate": 4.922325694166119e-05,
      "loss": 0.6471,
      "step": 100
    },
    {
      "epoch": 0.2504472271914132,
      "grad_norm": 1.1198012828826904,
      "learning_rate": 4.9144098063852485e-05,
      "loss": 0.6456,
      "step": 105
    },
    {
      "epoch": 0.26237328562909956,
      "grad_norm": 1.1725982427597046,
      "learning_rate": 4.9061168897977564e-05,
      "loss": 0.6462,
      "step": 110
    },
    {
      "epoch": 0.2742993440667859,
      "grad_norm": 0.9855665564537048,
      "learning_rate": 4.8974482394068514e-05,
      "loss": 0.6594,
      "step": 115
    },
    {
      "epoch": 0.28622540250447226,
      "grad_norm": 0.8321542739868164,
      "learning_rate": 4.888405208889486e-05,
      "loss": 0.6372,
      "step": 120
    },
    {
      "epoch": 0.2981514609421586,
      "grad_norm": 0.9451864957809448,
      "learning_rate": 4.878989210384972e-05,
      "loss": 0.6594,
      "step": 125
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.1336216926574707,
      "learning_rate": 4.869201714274467e-05,
      "loss": 0.6544,
      "step": 130
    },
    {
      "epoch": 0.3220035778175313,
      "grad_norm": 0.8466928601264954,
      "learning_rate": 4.8590442489513543e-05,
      "loss": 0.6275,
      "step": 135
    },
    {
      "epoch": 0.33392963625521765,
      "grad_norm": 0.979365885257721,
      "learning_rate": 4.8485184005825815e-05,
      "loss": 0.6348,
      "step": 140
    },
    {
      "epoch": 0.345855694692904,
      "grad_norm": 0.9159572124481201,
      "learning_rate": 4.837625812860961e-05,
      "loss": 0.6045,
      "step": 145
    },
    {
      "epoch": 0.35778175313059035,
      "grad_norm": 1.0542089939117432,
      "learning_rate": 4.8263681867485e-05,
      "loss": 0.6487,
      "step": 150
    },
    {
      "epoch": 0.3697078115682767,
      "grad_norm": 1.0264719724655151,
      "learning_rate": 4.814747280210782e-05,
      "loss": 0.6026,
      "step": 155
    },
    {
      "epoch": 0.38163387000596305,
      "grad_norm": 0.9389889240264893,
      "learning_rate": 4.80276490794244e-05,
      "loss": 0.6083,
      "step": 160
    },
    {
      "epoch": 0.3935599284436494,
      "grad_norm": 1.1090476512908936,
      "learning_rate": 4.790422941083786e-05,
      "loss": 0.5957,
      "step": 165
    },
    {
      "epoch": 0.4054859868813357,
      "grad_norm": 1.0268605947494507,
      "learning_rate": 4.7777233069286154e-05,
      "loss": 0.6538,
      "step": 170
    },
    {
      "epoch": 0.41741204531902204,
      "grad_norm": 1.240955114364624,
      "learning_rate": 4.7646679886232414e-05,
      "loss": 0.62,
      "step": 175
    },
    {
      "epoch": 0.4293381037567084,
      "grad_norm": 1.2029043436050415,
      "learning_rate": 4.7512590248568163e-05,
      "loss": 0.6461,
      "step": 180
    },
    {
      "epoch": 0.44126416219439474,
      "grad_norm": 1.0567660331726074,
      "learning_rate": 4.7374985095429725e-05,
      "loss": 0.633,
      "step": 185
    },
    {
      "epoch": 0.4531902206320811,
      "grad_norm": 0.928354024887085,
      "learning_rate": 4.723388591492841e-05,
      "loss": 0.633,
      "step": 190
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.8453586101531982,
      "learning_rate": 4.708931474079499e-05,
      "loss": 0.6082,
      "step": 195
    },
    {
      "epoch": 0.4770423375074538,
      "grad_norm": 1.33816397190094,
      "learning_rate": 4.6941294148938954e-05,
      "loss": 0.6176,
      "step": 200
    },
    {
      "epoch": 0.48896839594514013,
      "grad_norm": 0.9532414078712463,
      "learning_rate": 4.678984725392309e-05,
      "loss": 0.6168,
      "step": 205
    },
    {
      "epoch": 0.5008944543828264,
      "grad_norm": 0.9017360210418701,
      "learning_rate": 4.6634997705354024e-05,
      "loss": 0.6454,
      "step": 210
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 1.1095216274261475,
      "learning_rate": 4.6476769684189065e-05,
      "loss": 0.5738,
      "step": 215
    },
    {
      "epoch": 0.5247465712581991,
      "grad_norm": 0.8017715811729431,
      "learning_rate": 4.631518789896023e-05,
      "loss": 0.5978,
      "step": 220
    },
    {
      "epoch": 0.5366726296958855,
      "grad_norm": 1.0233415365219116,
      "learning_rate": 4.6150277581915804e-05,
      "loss": 0.6375,
      "step": 225
    },
    {
      "epoch": 0.5485986881335718,
      "grad_norm": 0.9298461675643921,
      "learning_rate": 4.598206448508007e-05,
      "loss": 0.606,
      "step": 230
    },
    {
      "epoch": 0.5605247465712582,
      "grad_norm": 0.9300760626792908,
      "learning_rate": 4.581057487623204e-05,
      "loss": 0.6261,
      "step": 235
    },
    {
      "epoch": 0.5724508050089445,
      "grad_norm": 1.4629548788070679,
      "learning_rate": 4.5635835534803406e-05,
      "loss": 0.5877,
      "step": 240
    },
    {
      "epoch": 0.5843768634466309,
      "grad_norm": 0.916437029838562,
      "learning_rate": 4.545787374769686e-05,
      "loss": 0.5821,
      "step": 245
    },
    {
      "epoch": 0.5963029218843172,
      "grad_norm": 0.9588505625724792,
      "learning_rate": 4.527671730502491e-05,
      "loss": 0.6126,
      "step": 250
    },
    {
      "epoch": 0.6082289803220036,
      "grad_norm": 1.068697214126587,
      "learning_rate": 4.5092394495770335e-05,
      "loss": 0.6034,
      "step": 255
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 0.816047191619873,
      "learning_rate": 4.490493410336857e-05,
      "loss": 0.6088,
      "step": 260
    },
    {
      "epoch": 0.6320810971973763,
      "grad_norm": 0.8465267419815063,
      "learning_rate": 4.4714365401213e-05,
      "loss": 0.6067,
      "step": 265
    },
    {
      "epoch": 0.6440071556350626,
      "grad_norm": 0.9819373488426208,
      "learning_rate": 4.4520718148083665e-05,
      "loss": 0.6334,
      "step": 270
    },
    {
      "epoch": 0.655933214072749,
      "grad_norm": 0.7895939350128174,
      "learning_rate": 4.43240225835002e-05,
      "loss": 0.6093,
      "step": 275
    },
    {
      "epoch": 0.6678592725104353,
      "grad_norm": 1.0516682863235474,
      "learning_rate": 4.41243094229997e-05,
      "loss": 0.5939,
      "step": 280
    },
    {
      "epoch": 0.6797853309481217,
      "grad_norm": 0.8521412014961243,
      "learning_rate": 4.392160985334027e-05,
      "loss": 0.5483,
      "step": 285
    },
    {
      "epoch": 0.691711389385808,
      "grad_norm": 0.847909152507782,
      "learning_rate": 4.371595552763093e-05,
      "loss": 0.5946,
      "step": 290
    },
    {
      "epoch": 0.7036374478234944,
      "grad_norm": 1.1502934694290161,
      "learning_rate": 4.350737856038878e-05,
      "loss": 0.5651,
      "step": 295
    },
    {
      "epoch": 0.7155635062611807,
      "grad_norm": 1.0434402227401733,
      "learning_rate": 4.3295911522524044e-05,
      "loss": 0.5965,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 1257,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.045581627654144e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}