{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1188118811881188,
  "eval_steps": 42,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002828854314002829,
      "eval_loss": 11.916790962219238,
      "eval_runtime": 6.6784,
      "eval_samples_per_second": 89.243,
      "eval_steps_per_second": 11.23,
      "step": 1
    },
    {
      "epoch": 0.008486562942008486,
      "grad_norm": 0.5188692212104797,
      "learning_rate": 3e-05,
      "loss": 11.92,
      "step": 3
    },
    {
      "epoch": 0.016973125884016973,
      "grad_norm": 0.48136115074157715,
      "learning_rate": 6e-05,
      "loss": 11.9198,
      "step": 6
    },
    {
      "epoch": 0.02545968882602546,
      "grad_norm": 0.5018041729927063,
      "learning_rate": 9e-05,
      "loss": 11.9077,
      "step": 9
    },
    {
      "epoch": 0.033946251768033946,
      "grad_norm": 0.6158789992332458,
      "learning_rate": 9.999588943391597e-05,
      "loss": 11.9074,
      "step": 12
    },
    {
      "epoch": 0.042432814710042434,
      "grad_norm": 0.6823853850364685,
      "learning_rate": 9.99743108100344e-05,
      "loss": 11.9042,
      "step": 15
    },
    {
      "epoch": 0.05091937765205092,
      "grad_norm": 0.8695465922355652,
      "learning_rate": 9.993424445916923e-05,
      "loss": 11.8991,
      "step": 18
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 0.9028195142745972,
      "learning_rate": 9.987570520365104e-05,
      "loss": 11.8853,
      "step": 21
    },
    {
      "epoch": 0.06789250353606789,
      "grad_norm": 0.9360626935958862,
      "learning_rate": 9.979871469976196e-05,
      "loss": 11.8781,
      "step": 24
    },
    {
      "epoch": 0.07637906647807638,
      "grad_norm": 0.8196120858192444,
      "learning_rate": 9.970330142972401e-05,
      "loss": 11.8677,
      "step": 27
    },
    {
      "epoch": 0.08486562942008487,
      "grad_norm": 0.7162870168685913,
      "learning_rate": 9.95895006911623e-05,
      "loss": 11.8614,
      "step": 30
    },
    {
      "epoch": 0.09335219236209336,
      "grad_norm": 0.5132609605789185,
      "learning_rate": 9.945735458404681e-05,
      "loss": 11.8498,
      "step": 33
    },
    {
      "epoch": 0.10183875530410184,
      "grad_norm": 0.4584226608276367,
      "learning_rate": 9.930691199511775e-05,
      "loss": 11.8467,
      "step": 36
    },
    {
      "epoch": 0.11032531824611033,
      "grad_norm": 0.29786884784698486,
      "learning_rate": 9.91382285798002e-05,
      "loss": 11.8511,
      "step": 39
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 0.2889010012149811,
      "learning_rate": 9.895136674161465e-05,
      "loss": 11.8408,
      "step": 42
    },
    {
      "epoch": 0.1188118811881188,
      "eval_loss": 11.839421272277832,
      "eval_runtime": 6.332,
      "eval_samples_per_second": 94.125,
      "eval_steps_per_second": 11.845,
      "step": 42
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 254298685440.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}