{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.991869918699187,
  "eval_steps": 500,
  "global_step": 276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10840108401084012,
      "grad_norm": 1.2238898092954031,
      "learning_rate": 5e-06,
      "loss": 1.1139,
      "step": 10
    },
    {
      "epoch": 0.21680216802168023,
      "grad_norm": 0.7661987078288646,
      "learning_rate": 5e-06,
      "loss": 1.0234,
      "step": 20
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 0.6931478916835131,
      "learning_rate": 5e-06,
      "loss": 1.0067,
      "step": 30
    },
    {
      "epoch": 0.43360433604336046,
      "grad_norm": 0.6288766129904495,
      "learning_rate": 5e-06,
      "loss": 1.0004,
      "step": 40
    },
    {
      "epoch": 0.5420054200542005,
      "grad_norm": 0.6511705997239466,
      "learning_rate": 5e-06,
      "loss": 0.9872,
      "step": 50
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 0.6237606284279241,
      "learning_rate": 5e-06,
      "loss": 0.983,
      "step": 60
    },
    {
      "epoch": 0.7588075880758808,
      "grad_norm": 0.6061811934000912,
      "learning_rate": 5e-06,
      "loss": 0.977,
      "step": 70
    },
    {
      "epoch": 0.8672086720867209,
      "grad_norm": 0.5691567098461193,
      "learning_rate": 5e-06,
      "loss": 0.9609,
      "step": 80
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.579566994994573,
      "learning_rate": 5e-06,
      "loss": 0.967,
      "step": 90
    },
    {
      "epoch": 0.997289972899729,
      "eval_loss": 0.9647226333618164,
      "eval_runtime": 97.7674,
      "eval_samples_per_second": 25.417,
      "eval_steps_per_second": 0.399,
      "step": 92
    },
    {
      "epoch": 1.084010840108401,
      "grad_norm": 0.7893915919770154,
      "learning_rate": 5e-06,
      "loss": 1.0085,
      "step": 100
    },
    {
      "epoch": 1.1924119241192412,
      "grad_norm": 0.6881452344372211,
      "learning_rate": 5e-06,
      "loss": 0.9266,
      "step": 110
    },
    {
      "epoch": 1.3008130081300813,
      "grad_norm": 0.7094638595829068,
      "learning_rate": 5e-06,
      "loss": 0.9176,
      "step": 120
    },
    {
      "epoch": 1.4092140921409215,
      "grad_norm": 0.757737014933452,
      "learning_rate": 5e-06,
      "loss": 0.9165,
      "step": 130
    },
    {
      "epoch": 1.5176151761517616,
      "grad_norm": 0.7420578994185969,
      "learning_rate": 5e-06,
      "loss": 0.9178,
      "step": 140
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 0.6872431636486115,
      "learning_rate": 5e-06,
      "loss": 0.9095,
      "step": 150
    },
    {
      "epoch": 1.7344173441734418,
      "grad_norm": 0.6839268163247622,
      "learning_rate": 5e-06,
      "loss": 0.922,
      "step": 160
    },
    {
      "epoch": 1.8428184281842819,
      "grad_norm": 0.6646443132529639,
      "learning_rate": 5e-06,
      "loss": 0.9161,
      "step": 170
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.7695800503499497,
      "learning_rate": 5e-06,
      "loss": 0.917,
      "step": 180
    },
    {
      "epoch": 1.994579945799458,
      "eval_loss": 0.9558340907096863,
      "eval_runtime": 98.5336,
      "eval_samples_per_second": 25.22,
      "eval_steps_per_second": 0.396,
      "step": 184
    },
    {
      "epoch": 2.059620596205962,
      "grad_norm": 0.8673539202787472,
      "learning_rate": 5e-06,
      "loss": 0.9576,
      "step": 190
    },
    {
      "epoch": 2.168021680216802,
      "grad_norm": 0.6595504985017855,
      "learning_rate": 5e-06,
      "loss": 0.8711,
      "step": 200
    },
    {
      "epoch": 2.2764227642276422,
      "grad_norm": 0.7339078950029295,
      "learning_rate": 5e-06,
      "loss": 0.8692,
      "step": 210
    },
    {
      "epoch": 2.3848238482384825,
      "grad_norm": 0.7590090712265437,
      "learning_rate": 5e-06,
      "loss": 0.8727,
      "step": 220
    },
    {
      "epoch": 2.4932249322493227,
      "grad_norm": 0.6567177012645716,
      "learning_rate": 5e-06,
      "loss": 0.8714,
      "step": 230
    },
    {
      "epoch": 2.6016260162601625,
      "grad_norm": 0.7927473560858851,
      "learning_rate": 5e-06,
      "loss": 0.8675,
      "step": 240
    },
    {
      "epoch": 2.710027100271003,
      "grad_norm": 0.6928632841645139,
      "learning_rate": 5e-06,
      "loss": 0.8694,
      "step": 250
    },
    {
      "epoch": 2.818428184281843,
      "grad_norm": 0.7142607867077723,
      "learning_rate": 5e-06,
      "loss": 0.8728,
      "step": 260
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 0.7218062765913728,
      "learning_rate": 5e-06,
      "loss": 0.8735,
      "step": 270
    },
    {
      "epoch": 2.991869918699187,
      "eval_loss": 0.9591670632362366,
      "eval_runtime": 96.4736,
      "eval_samples_per_second": 25.758,
      "eval_steps_per_second": 0.404,
      "step": 276
    },
    {
      "epoch": 2.991869918699187,
      "step": 276,
      "total_flos": 462100900085760.0,
      "train_loss": 0.935515574786974,
      "train_runtime": 16221.6629,
      "train_samples_per_second": 8.73,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 276,
  "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": 462100900085760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}