{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.3701596260070801,
      "learning_rate": 2e-05,
      "loss": 1.2482,
      "step": 5
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.22348932921886444,
      "learning_rate": 2e-05,
      "loss": 1.0639,
      "step": 10
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.30826476216316223,
      "learning_rate": 2e-05,
      "loss": 0.975,
      "step": 15
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.19094961881637573,
      "learning_rate": 2e-05,
      "loss": 1.0374,
      "step": 20
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.18843892216682434,
      "learning_rate": 2e-05,
      "loss": 0.9062,
      "step": 25
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.15660837292671204,
      "learning_rate": 2e-05,
      "loss": 0.8813,
      "step": 30
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.2319907695055008,
      "learning_rate": 2e-05,
      "loss": 0.9589,
      "step": 35
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.20357345044612885,
      "learning_rate": 2e-05,
      "loss": 0.9257,
      "step": 40
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.16901366412639618,
      "learning_rate": 2e-05,
      "loss": 0.8194,
      "step": 45
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.24122780561447144,
      "learning_rate": 2e-05,
      "loss": 0.8726,
      "step": 50
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.21689686179161072,
      "learning_rate": 2e-05,
      "loss": 0.9835,
      "step": 55
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.18955062329769135,
      "learning_rate": 2e-05,
      "loss": 0.8624,
      "step": 60
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 0.2065642923116684,
      "learning_rate": 2e-05,
      "loss": 0.8287,
      "step": 65
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.18894456326961517,
      "learning_rate": 2e-05,
      "loss": 0.981,
      "step": 70
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.17258857190608978,
      "learning_rate": 2e-05,
      "loss": 0.8652,
      "step": 75
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.1549784541130066,
      "learning_rate": 2e-05,
      "loss": 0.8775,
      "step": 80
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 0.18814615905284882,
      "learning_rate": 2e-05,
      "loss": 0.9429,
      "step": 85
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.18734842538833618,
      "learning_rate": 2e-05,
      "loss": 0.8884,
      "step": 90
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 0.1647917777299881,
      "learning_rate": 2e-05,
      "loss": 0.8504,
      "step": 95
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.24890270829200745,
      "learning_rate": 2e-05,
      "loss": 0.8224,
      "step": 100
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 0.20458489656448364,
      "learning_rate": 2e-05,
      "loss": 0.9412,
      "step": 105
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.18102170526981354,
      "learning_rate": 2e-05,
      "loss": 0.8754,
      "step": 110
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 0.17741850018501282,
      "learning_rate": 2e-05,
      "loss": 0.8302,
      "step": 115
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.20435400307178497,
      "learning_rate": 2e-05,
      "loss": 0.9222,
      "step": 120
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.19005118310451508,
      "learning_rate": 2e-05,
      "loss": 0.8278,
      "step": 125
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.17868107557296753,
      "learning_rate": 2e-05,
      "loss": 0.8354,
      "step": 130
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 0.1938895732164383,
      "learning_rate": 2e-05,
      "loss": 0.902,
      "step": 135
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.18117573857307434,
      "learning_rate": 2e-05,
      "loss": 0.8911,
      "step": 140
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 0.21764567494392395,
      "learning_rate": 2e-05,
      "loss": 0.8493,
      "step": 145
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.3313971161842346,
      "learning_rate": 2e-05,
      "loss": 0.8318,
      "step": 150
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 0.22705790400505066,
      "learning_rate": 2e-05,
      "loss": 0.9222,
      "step": 155
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.183769091963768,
      "learning_rate": 2e-05,
      "loss": 0.8331,
      "step": 160
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 0.17954127490520477,
      "learning_rate": 2e-05,
      "loss": 0.8094,
      "step": 165
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.1975155919790268,
      "learning_rate": 2e-05,
      "loss": 0.8994,
      "step": 170
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.21705932915210724,
      "learning_rate": 2e-05,
      "loss": 0.797,
      "step": 175
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.18831680715084076,
      "learning_rate": 2e-05,
      "loss": 0.8198,
      "step": 180
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 0.23201768100261688,
      "learning_rate": 2e-05,
      "loss": 0.8965,
      "step": 185
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.20603500306606293,
      "learning_rate": 2e-05,
      "loss": 0.8632,
      "step": 190
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 0.19485333561897278,
      "learning_rate": 2e-05,
      "loss": 0.8264,
      "step": 195
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.23732714354991913,
      "learning_rate": 2e-05,
      "loss": 0.8268,
      "step": 200
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 0.22331510484218597,
      "learning_rate": 2e-05,
      "loss": 0.9291,
      "step": 205
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.18885022401809692,
      "learning_rate": 2e-05,
      "loss": 0.8126,
      "step": 210
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.19218967854976654,
      "learning_rate": 2e-05,
      "loss": 0.8162,
      "step": 215
    }
  ],
  "logging_steps": 5,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 99999,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1971222282777395e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}