{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2767783005812344,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011071132023249377,
      "grad_norm": 0.2982485890388489,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5438612461090088,
      "step": 10
    },
    {
      "epoch": 0.022142264046498755,
      "grad_norm": 0.2238633632659912,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.4879115104675293,
      "step": 20
    },
    {
      "epoch": 0.03321339606974813,
      "grad_norm": 0.19642046093940735,
      "learning_rate": 4.9999358393573445e-05,
      "loss": 0.5164765357971192,
      "step": 30
    },
    {
      "epoch": 0.04428452809299751,
      "grad_norm": 0.17894092202186584,
      "learning_rate": 4.997690562638874e-05,
      "loss": 0.5168572425842285,
      "step": 40
    },
    {
      "epoch": 0.05535566011624689,
      "grad_norm": 0.20002231001853943,
      "learning_rate": 4.992240546298341e-05,
      "loss": 0.4712099552154541,
      "step": 50
    },
    {
      "epoch": 0.06642679213949626,
      "grad_norm": 0.18889793753623962,
      "learning_rate": 4.983592783148856e-05,
      "loss": 0.4723380088806152,
      "step": 60
    },
    {
      "epoch": 0.07749792416274565,
      "grad_norm": 0.1800369769334793,
      "learning_rate": 4.9717583689721046e-05,
      "loss": 0.4957925319671631,
      "step": 70
    },
    {
      "epoch": 0.08856905618599502,
      "grad_norm": 0.18672174215316772,
      "learning_rate": 4.9567524882815686e-05,
      "loss": 0.4966912269592285,
      "step": 80
    },
    {
      "epoch": 0.09964018820924439,
      "grad_norm": 0.19791601598262787,
      "learning_rate": 4.938594394839555e-05,
      "loss": 0.45592079162597654,
      "step": 90
    },
    {
      "epoch": 0.11071132023249378,
      "grad_norm": 0.17983797192573547,
      "learning_rate": 4.917307386953062e-05,
      "loss": 0.47900638580322263,
      "step": 100
    },
    {
      "epoch": 0.12178245225574315,
      "grad_norm": 0.19228127598762512,
      "learning_rate": 4.892918777580161e-05,
      "loss": 0.47019343376159667,
      "step": 110
    },
    {
      "epoch": 0.13285358427899252,
      "grad_norm": 0.19917553663253784,
      "learning_rate": 4.865459859285251e-05,
      "loss": 0.5000853061676025,
      "step": 120
    },
    {
      "epoch": 0.1439247163022419,
      "grad_norm": 0.19071853160858154,
      "learning_rate": 4.834965864088164e-05,
      "loss": 0.45295085906982424,
      "step": 130
    },
    {
      "epoch": 0.1549958483254913,
      "grad_norm": 0.16079416871070862,
      "learning_rate": 4.8014759182586274e-05,
      "loss": 0.4652396202087402,
      "step": 140
    },
    {
      "epoch": 0.16606698034874065,
      "grad_norm": 0.19701199233531952,
      "learning_rate": 4.765032992114078e-05,
      "loss": 0.48296642303466797,
      "step": 150
    },
    {
      "epoch": 0.17713811237199004,
      "grad_norm": 0.21357282996177673,
      "learning_rate": 4.725683844885266e-05,
      "loss": 0.49079251289367676,
      "step": 160
    },
    {
      "epoch": 0.18820924439523942,
      "grad_norm": 0.2039526402950287,
      "learning_rate": 4.6834789647203656e-05,
      "loss": 0.4890737056732178,
      "step": 170
    },
    {
      "epoch": 0.19928037641848878,
      "grad_norm": 0.21518221497535706,
      "learning_rate": 4.638472503904583e-05,
      "loss": 0.45900492668151854,
      "step": 180
    },
    {
      "epoch": 0.21035150844173817,
      "grad_norm": 0.21490415930747986,
      "learning_rate": 4.590722209378387e-05,
      "loss": 0.5259706974029541,
      "step": 190
    },
    {
      "epoch": 0.22142264046498755,
      "grad_norm": 0.168563112616539,
      "learning_rate": 4.540289348643493e-05,
      "loss": 0.460019588470459,
      "step": 200
    },
    {
      "epoch": 0.2324937724882369,
      "grad_norm": 0.1914004385471344,
      "learning_rate": 4.487238631151691e-05,
      "loss": 0.44524073600769043,
      "step": 210
    },
    {
      "epoch": 0.2435649045114863,
      "grad_norm": 0.17691361904144287,
      "learning_rate": 4.4316381252773696e-05,
      "loss": 0.46790690422058107,
      "step": 220
    },
    {
      "epoch": 0.25463603653473565,
      "grad_norm": 0.2210698425769806,
      "learning_rate": 4.373559170980271e-05,
      "loss": 0.4862049579620361,
      "step": 230
    },
    {
      "epoch": 0.26570716855798504,
      "grad_norm": 0.22967994213104248,
      "learning_rate": 4.3130762882705286e-05,
      "loss": 0.4924201011657715,
      "step": 240
    },
    {
      "epoch": 0.2767783005812344,
      "grad_norm": 0.16751348972320557,
      "learning_rate": 4.2502670815934566e-05,
      "loss": 0.4716155529022217,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 904,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.135427445782528e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}