{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08533333333333333,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008533333333333334,
      "grad_norm": 231.34270101410158,
      "learning_rate": 0.0,
      "loss": 8.0033,
      "step": 1
    },
    {
      "epoch": 0.017066666666666667,
      "grad_norm": 222.45613156024717,
      "learning_rate": 3.010299956639811e-07,
      "loss": 8.0428,
      "step": 2
    },
    {
      "epoch": 0.0256,
      "grad_norm": 215.11231622980122,
      "learning_rate": 4.771212547196623e-07,
      "loss": 8.1972,
      "step": 3
    },
    {
      "epoch": 0.034133333333333335,
      "grad_norm": 219.60924103962475,
      "learning_rate": 6.020599913279622e-07,
      "loss": 7.9839,
      "step": 4
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 215.38857509452538,
      "learning_rate": 6.989700043360186e-07,
      "loss": 7.9458,
      "step": 5
    },
    {
      "epoch": 0.0512,
      "grad_norm": 216.6292736162405,
      "learning_rate": 7.781512503836435e-07,
      "loss": 8.0918,
      "step": 6
    },
    {
      "epoch": 0.05973333333333333,
      "grad_norm": 221.48329860849555,
      "learning_rate": 8.450980400142567e-07,
      "loss": 7.6396,
      "step": 7
    },
    {
      "epoch": 0.06826666666666667,
      "grad_norm": 209.19887181519408,
      "learning_rate": 9.030899869919433e-07,
      "loss": 7.9538,
      "step": 8
    },
    {
      "epoch": 0.0768,
      "grad_norm": 212.49168182248923,
      "learning_rate": 9.542425094393247e-07,
      "loss": 7.956,
      "step": 9
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 210.10834258781824,
      "learning_rate": 9.999999999999997e-07,
      "loss": 7.8862,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 301,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.596511596010537e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}