{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.253968253968254,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.021825501695275307,
      "learning_rate": 4.95e-06,
      "loss": 0.0099,
      "on_policy_loss": 0.0099,
      "step": 2
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.030356515198946,
      "learning_rate": 4.85e-06,
      "loss": 0.0109,
      "on_policy_loss": 0.0109,
      "step": 4
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.03628372400999069,
      "learning_rate": 4.75e-06,
      "loss": 0.011,
      "on_policy_loss": 0.011,
      "step": 6
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.016426855698227882,
      "learning_rate": 4.65e-06,
      "loss": 0.0086,
      "on_policy_loss": 0.0086,
      "step": 8
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.020383551716804504,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0083,
      "on_policy_loss": 0.0083,
      "step": 10
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.01429930329322815,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.008,
      "on_policy_loss": 0.008,
      "step": 12
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.012996818870306015,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0062,
      "on_policy_loss": 0.0062,
      "step": 14
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.023571355268359184,
      "learning_rate": 4.25e-06,
      "loss": 0.0049,
      "on_policy_loss": 0.0056,
      "step": 16
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 0.00921392161399126,
      "learning_rate": 4.15e-06,
      "loss": 0.0048,
      "on_policy_loss": 0.0048,
      "step": 18
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 0.01190966833382845,
      "learning_rate": 4.05e-06,
      "loss": 0.0044,
      "on_policy_loss": 0.0044,
      "step": 20
    }
  ],
  "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
}