{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02442002442002442,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002442002442002442,
      "grad_norm": 5.134684085845947,
      "learning_rate": 2e-05,
      "loss": 9.0684,
      "step": 1
    },
    {
      "epoch": 0.002442002442002442,
      "eval_loss": 2.1976280212402344,
      "eval_runtime": 37.4303,
      "eval_samples_per_second": 4.622,
      "eval_steps_per_second": 2.324,
      "step": 1
    },
    {
      "epoch": 0.004884004884004884,
      "grad_norm": 2.9778659343719482,
      "learning_rate": 4e-05,
      "loss": 6.4046,
      "step": 2
    },
    {
      "epoch": 0.007326007326007326,
      "grad_norm": 1.9320050477981567,
      "learning_rate": 6e-05,
      "loss": 4.8923,
      "step": 3
    },
    {
      "epoch": 0.007326007326007326,
      "eval_loss": 2.1948463916778564,
      "eval_runtime": 37.5368,
      "eval_samples_per_second": 4.609,
      "eval_steps_per_second": 2.318,
      "step": 3
    },
    {
      "epoch": 0.009768009768009768,
      "grad_norm": 3.2159366607666016,
      "learning_rate": 8e-05,
      "loss": 7.6618,
      "step": 4
    },
    {
      "epoch": 0.01221001221001221,
      "grad_norm": 3.0355820655822754,
      "learning_rate": 0.0001,
      "loss": 6.446,
      "step": 5
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 3.326921224594116,
      "learning_rate": 0.00012,
      "loss": 6.1661,
      "step": 6
    },
    {
      "epoch": 0.014652014652014652,
      "eval_loss": 2.1506800651550293,
      "eval_runtime": 41.321,
      "eval_samples_per_second": 4.187,
      "eval_steps_per_second": 2.105,
      "step": 6
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 5.84164571762085,
      "learning_rate": 0.00014,
      "loss": 11.5528,
      "step": 7
    },
    {
      "epoch": 0.019536019536019536,
      "grad_norm": 4.878077983856201,
      "learning_rate": 0.00016,
      "loss": 6.6154,
      "step": 8
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 3.949739694595337,
      "learning_rate": 0.00018,
      "loss": 6.7579,
      "step": 9
    },
    {
      "epoch": 0.02197802197802198,
      "eval_loss": 1.9544545412063599,
      "eval_runtime": 37.4802,
      "eval_samples_per_second": 4.616,
      "eval_steps_per_second": 2.321,
      "step": 9
    },
    {
      "epoch": 0.02442002442002442,
      "grad_norm": 6.677595138549805,
      "learning_rate": 0.0002,
      "loss": 11.3436,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6174098136760320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}