{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021333333333333333,
      "grad_norm": 0.13489535450935364,
      "learning_rate": 4.95e-06,
      "loss": 0.0012,
      "on_policy_loss": 0.0012,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.14185190200805664,
      "learning_rate": 4.85e-06,
      "loss": 0.0024,
      "on_policy_loss": 0.0024,
      "step": 4
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.059850700199604034,
      "learning_rate": 4.75e-06,
      "loss": 0.0014,
      "on_policy_loss": 0.0014,
      "step": 6
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.08647190779447556,
      "learning_rate": 4.65e-06,
      "loss": 0.0003,
      "on_policy_loss": 0.0003,
      "step": 8
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.07889997214078903,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0002,
      "on_policy_loss": 0.0002,
      "step": 10
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.12323067337274551,
      "learning_rate": 4.450000000000001e-06,
      "loss": -0.0005,
      "on_policy_loss": -0.0005,
      "step": 12
    },
    {
      "epoch": 0.14933333333333335,
      "grad_norm": 0.11012116074562073,
      "learning_rate": 4.350000000000001e-06,
      "loss": -0.0007,
      "on_policy_loss": -0.0007,
      "step": 14
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.20869049429893494,
      "learning_rate": 4.25e-06,
      "loss": -0.0014,
      "on_policy_loss": -0.0014,
      "step": 16
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.0413811095058918,
      "learning_rate": 4.15e-06,
      "loss": -0.0019,
      "on_policy_loss": -0.0019,
      "step": 18
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.03595610707998276,
      "learning_rate": 4.05e-06,
      "loss": -0.0019,
      "on_policy_loss": -0.0019,
      "step": 20
    },
    {
      "epoch": 0.23466666666666666,
      "grad_norm": 0.03915691003203392,
      "learning_rate": 3.95e-06,
      "loss": -0.0028,
      "on_policy_loss": -0.0028,
      "step": 22
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.0527644082903862,
      "learning_rate": 3.85e-06,
      "loss": -0.0027,
      "on_policy_loss": -0.0027,
      "step": 24
    },
    {
      "epoch": 0.2773333333333333,
      "grad_norm": 0.031156938523054123,
      "learning_rate": 3.7500000000000005e-06,
      "loss": -0.0035,
      "on_policy_loss": -0.0035,
      "step": 26
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.0408235602080822,
      "learning_rate": 3.65e-06,
      "loss": -0.0036,
      "on_policy_loss": -0.0036,
      "step": 28
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.0373714454472065,
      "learning_rate": 3.5500000000000003e-06,
      "loss": -0.0038,
      "on_policy_loss": -0.0038,
      "step": 30
    }
  ],
  "logging_steps": 2,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}