{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5714285714285714,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.02300829067826271,
      "learning_rate": 4.95e-06,
      "loss": 0.0077,
      "on_policy_loss": 0.0077,
      "step": 2
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.014391576871275902,
      "learning_rate": 4.85e-06,
      "loss": 0.0098,
      "on_policy_loss": 0.0098,
      "step": 4
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.02317691408097744,
      "learning_rate": 4.75e-06,
      "loss": 0.0091,
      "on_policy_loss": 0.0091,
      "step": 6
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.02184865064918995,
      "learning_rate": 4.65e-06,
      "loss": 0.0076,
      "on_policy_loss": 0.0076,
      "step": 8
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.015297573059797287,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0076,
      "on_policy_loss": 0.0076,
      "step": 10
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.01648167334496975,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0058,
      "on_policy_loss": 0.0058,
      "step": 12
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.013269731774926186,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0052,
      "on_policy_loss": 0.0052,
      "step": 14
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.01989767700433731,
      "learning_rate": 4.25e-06,
      "loss": 0.0048,
      "on_policy_loss": 0.0055,
      "step": 16
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 0.011844882741570473,
      "learning_rate": 4.15e-06,
      "loss": 0.0034,
      "on_policy_loss": 0.0034,
      "step": 18
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 0.01972465217113495,
      "learning_rate": 4.05e-06,
      "loss": 0.0031,
      "on_policy_loss": 0.0031,
      "step": 20
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.01844724826514721,
      "learning_rate": 3.95e-06,
      "loss": 0.002,
      "on_policy_loss": 0.002,
      "step": 22
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 0.018438735976815224,
      "learning_rate": 3.85e-06,
      "loss": 0.0014,
      "on_policy_loss": 0.0014,
      "step": 24
    }
  ],
  "logging_steps": 2,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}