{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 228,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 8.477547407637145,
      "learning_rate": 7.82608695652174e-06,
      "loss": 1.5102,
      "step": 10
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 2.7741164985922446,
      "learning_rate": 1.6521739130434785e-05,
      "loss": 0.8919,
      "step": 20
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 2.056306394468331,
      "learning_rate": 1.9957756633258264e-05,
      "loss": 0.8216,
      "step": 30
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 2.146307741121485,
      "learning_rate": 1.9700894071491736e-05,
      "loss": 0.8108,
      "step": 40
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 2.066709337428477,
      "learning_rate": 1.9216650774785975e-05,
      "loss": 0.7918,
      "step": 50
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 3.4358972900426865,
      "learning_rate": 1.8516376995590185e-05,
      "loss": 0.7514,
      "step": 60
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 2.106209316347196,
      "learning_rate": 1.7616486557764187e-05,
      "loss": 0.7833,
      "step": 70
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.4631406623409116,
      "learning_rate": 1.6538072130458853e-05,
      "loss": 0.7056,
      "step": 80
    },
    {
      "epoch": 1.1842105263157894,
      "grad_norm": 1.7317009771124054,
      "learning_rate": 1.5306410833828534e-05,
      "loss": 0.5845,
      "step": 90
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 1.6663659948073513,
      "learning_rate": 1.3950371764758543e-05,
      "loss": 0.603,
      "step": 100
    },
    {
      "epoch": 1.4473684210526316,
      "grad_norm": 1.5835467362397797,
      "learning_rate": 1.2501739329702453e-05,
      "loss": 0.5848,
      "step": 110
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 1.5087640437736358,
      "learning_rate": 1.0994468245134071e-05,
      "loss": 0.5757,
      "step": 120
    },
    {
      "epoch": 1.7105263157894737,
      "grad_norm": 1.6010692904865604,
      "learning_rate": 9.463887667771946e-06,
      "loss": 0.5573,
      "step": 130
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 1.518477136944885,
      "learning_rate": 7.945873109089503e-06,
      "loss": 0.5575,
      "step": 140
    },
    {
      "epoch": 1.973684210526316,
      "grad_norm": 1.410474762957939,
      "learning_rate": 6.476005543732783e-06,
      "loss": 0.5708,
      "step": 150
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.797519892522943,
      "learning_rate": 5.088737421631767e-06,
      "loss": 0.4269,
      "step": 160
    },
    {
      "epoch": 2.236842105263158,
      "grad_norm": 1.413640789584412,
      "learning_rate": 3.8165851317745705e-06,
      "loss": 0.3803,
      "step": 170
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 1.9426892837507217,
      "learning_rate": 2.6893668456091627e-06,
      "loss": 0.3743,
      "step": 180
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.568653298779716,
      "learning_rate": 1.7335036043773402e-06,
      "loss": 0.3636,
      "step": 190
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 1.7450539491612516,
      "learning_rate": 9.714000323014705e-07,
      "loss": 0.3721,
      "step": 200
    },
    {
      "epoch": 2.763157894736842,
      "grad_norm": 1.7361396176890889,
      "learning_rate": 4.209191911819688e-07,
      "loss": 0.3777,
      "step": 210
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 1.5748925163724883,
      "learning_rate": 9.496388536875623e-08,
      "loss": 0.3594,
      "step": 220
    }
  ],
  "logging_steps": 10,
  "max_steps": 228,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 14407662108672.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}