{
  "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": 1.7071588039398193,
      "learning_rate": 2e-05,
      "loss": 1.2071,
      "step": 5
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.3188117742538452,
      "learning_rate": 2e-05,
      "loss": 1.0864,
      "step": 10
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.2328031063079834,
      "learning_rate": 2e-05,
      "loss": 0.9077,
      "step": 15
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.3528258800506592,
      "learning_rate": 2e-05,
      "loss": 0.951,
      "step": 20
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.168439120054245,
      "learning_rate": 2e-05,
      "loss": 0.9764,
      "step": 25
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.14444082975387573,
      "learning_rate": 2e-05,
      "loss": 0.8102,
      "step": 30
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.2678701877593994,
      "learning_rate": 2e-05,
      "loss": 0.8644,
      "step": 35
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.2088869959115982,
      "learning_rate": 2e-05,
      "loss": 0.9437,
      "step": 40
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.14392392337322235,
      "learning_rate": 2e-05,
      "loss": 0.8126,
      "step": 45
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.31939807534217834,
      "learning_rate": 2e-05,
      "loss": 0.747,
      "step": 50
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.21644248068332672,
      "learning_rate": 2e-05,
      "loss": 0.908,
      "step": 55
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.14742884039878845,
      "learning_rate": 2e-05,
      "loss": 0.8698,
      "step": 60
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 0.18430279195308685,
      "learning_rate": 2e-05,
      "loss": 0.7584,
      "step": 65
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.3597599267959595,
      "learning_rate": 2e-05,
      "loss": 0.8581,
      "step": 70
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.15492893755435944,
      "learning_rate": 2e-05,
      "loss": 0.9204,
      "step": 75
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.147719144821167,
      "learning_rate": 2e-05,
      "loss": 0.7454,
      "step": 80
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 0.246868297457695,
      "learning_rate": 2e-05,
      "loss": 0.8537,
      "step": 85
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.17558737099170685,
      "learning_rate": 2e-05,
      "loss": 0.9411,
      "step": 90
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 0.15025165677070618,
      "learning_rate": 2e-05,
      "loss": 0.7557,
      "step": 95
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.29634204506874084,
      "learning_rate": 2e-05,
      "loss": 0.7418,
      "step": 100
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 0.18677298724651337,
      "learning_rate": 2e-05,
      "loss": 0.9445,
      "step": 105
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.1614491045475006,
      "learning_rate": 2e-05,
      "loss": 0.8228,
      "step": 110
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 0.18401965498924255,
      "learning_rate": 2e-05,
      "loss": 0.7213,
      "step": 115
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.22585374116897583,
      "learning_rate": 2e-05,
      "loss": 0.8905,
      "step": 120
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.1724023073911667,
      "learning_rate": 2e-05,
      "loss": 0.8981,
      "step": 125
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.14925441145896912,
      "learning_rate": 2e-05,
      "loss": 0.7038,
      "step": 130
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 0.2597886919975281,
      "learning_rate": 2e-05,
      "loss": 0.7908,
      "step": 135
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.17634142935276031,
      "learning_rate": 2e-05,
      "loss": 0.9247,
      "step": 140
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 0.16650615632534027,
      "learning_rate": 2e-05,
      "loss": 0.7638,
      "step": 145
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.2985098361968994,
      "learning_rate": 2e-05,
      "loss": 0.7397,
      "step": 150
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 0.20995645225048065,
      "learning_rate": 2e-05,
      "loss": 0.9161,
      "step": 155
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.16316258907318115,
      "learning_rate": 2e-05,
      "loss": 0.8105,
      "step": 160
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 0.18892395496368408,
      "learning_rate": 2e-05,
      "loss": 0.6916,
      "step": 165
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.23752492666244507,
      "learning_rate": 2e-05,
      "loss": 0.8452,
      "step": 170
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.18073770403862,
      "learning_rate": 2e-05,
      "loss": 0.8764,
      "step": 175
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.15237540006637573,
      "learning_rate": 2e-05,
      "loss": 0.7132,
      "step": 180
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 0.294465571641922,
      "learning_rate": 2e-05,
      "loss": 0.8096,
      "step": 185
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.263343870639801,
      "learning_rate": 2e-05,
      "loss": 0.8742,
      "step": 190
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 0.16255247592926025,
      "learning_rate": 2e-05,
      "loss": 0.733,
      "step": 195
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.33820098638534546,
      "learning_rate": 2e-05,
      "loss": 0.7324,
      "step": 200
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 0.2312634140253067,
      "learning_rate": 2e-05,
      "loss": 0.9044,
      "step": 205
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.2246032953262329,
      "learning_rate": 2e-05,
      "loss": 0.8323,
      "step": 210
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.20284949243068695,
      "learning_rate": 2e-05,
      "loss": 0.6975,
      "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": 2.8126845911380787e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}