{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1904761904761907,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.016652880236506462,
      "learning_rate": 4.95e-06,
      "loss": 0.0084,
      "on_policy_loss": 0.0084,
      "step": 2
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.023299429565668106,
      "learning_rate": 4.85e-06,
      "loss": 0.0096,
      "on_policy_loss": 0.0096,
      "step": 4
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.018967149779200554,
      "learning_rate": 4.75e-06,
      "loss": 0.0082,
      "on_policy_loss": 0.0082,
      "step": 6
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.01788295991718769,
      "learning_rate": 4.65e-06,
      "loss": 0.007,
      "on_policy_loss": 0.007,
      "step": 8
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.017450524494051933,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0075,
      "on_policy_loss": 0.0075,
      "step": 10
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.018722014501690865,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0067,
      "on_policy_loss": 0.0067,
      "step": 12
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.013490518555045128,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0065,
      "on_policy_loss": 0.0065,
      "step": 14
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.018299100920557976,
      "learning_rate": 4.25e-06,
      "loss": 0.0049,
      "on_policy_loss": 0.0056,
      "step": 16
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 0.01762264408171177,
      "learning_rate": 4.15e-06,
      "loss": 0.0044,
      "on_policy_loss": 0.0044,
      "step": 18
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 0.022086329758167267,
      "learning_rate": 4.05e-06,
      "loss": 0.0037,
      "on_policy_loss": 0.0037,
      "step": 20
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.016489138826727867,
      "learning_rate": 3.95e-06,
      "loss": 0.0028,
      "on_policy_loss": 0.0028,
      "step": 22
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 0.028454095125198364,
      "learning_rate": 3.85e-06,
      "loss": 0.0017,
      "on_policy_loss": 0.0017,
      "step": 24
    },
    {
      "epoch": 1.6349206349206349,
      "grad_norm": 0.02219998650252819,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0001,
      "on_policy_loss": 0.0001,
      "step": 26
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.02461564540863037,
      "learning_rate": 3.65e-06,
      "loss": -0.0021,
      "on_policy_loss": -0.0021,
      "step": 28
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.033813536167144775,
      "learning_rate": 3.5500000000000003e-06,
      "loss": -0.0064,
      "on_policy_loss": -0.0064,
      "step": 30
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04106909781694412,
      "learning_rate": 3.45e-06,
      "loss": -0.0083,
      "on_policy_loss": -0.0095,
      "step": 32
    },
    {
      "epoch": 2.126984126984127,
      "grad_norm": 0.028478125110268593,
      "learning_rate": 3.3500000000000005e-06,
      "loss": -0.01,
      "on_policy_loss": -0.01,
      "step": 34
    }
  ],
  "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
}