{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0163265306122449,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016326530612244899,
      "grad_norm": 7.402745246887207,
      "learning_rate": 2e-05,
      "loss": 12.742,
      "step": 1
    },
    {
      "epoch": 0.0016326530612244899,
      "eval_loss": 3.365116596221924,
      "eval_runtime": 16.8223,
      "eval_samples_per_second": 15.337,
      "eval_steps_per_second": 7.668,
      "step": 1
    },
    {
      "epoch": 0.0032653061224489797,
      "grad_norm": 2.5630970001220703,
      "learning_rate": 4e-05,
      "loss": 11.3295,
      "step": 2
    },
    {
      "epoch": 0.004897959183673469,
      "grad_norm": 6.483102798461914,
      "learning_rate": 6e-05,
      "loss": 12.9415,
      "step": 3
    },
    {
      "epoch": 0.004897959183673469,
      "eval_loss": 3.3538308143615723,
      "eval_runtime": 16.814,
      "eval_samples_per_second": 15.344,
      "eval_steps_per_second": 7.672,
      "step": 3
    },
    {
      "epoch": 0.006530612244897959,
      "grad_norm": 4.537841320037842,
      "learning_rate": 8e-05,
      "loss": 11.1569,
      "step": 4
    },
    {
      "epoch": 0.00816326530612245,
      "grad_norm": 9.974493980407715,
      "learning_rate": 0.0001,
      "loss": 14.1728,
      "step": 5
    },
    {
      "epoch": 0.009795918367346938,
      "grad_norm": 20.525466918945312,
      "learning_rate": 0.00012,
      "loss": 12.6136,
      "step": 6
    },
    {
      "epoch": 0.009795918367346938,
      "eval_loss": 2.8962912559509277,
      "eval_runtime": 16.8354,
      "eval_samples_per_second": 15.325,
      "eval_steps_per_second": 7.662,
      "step": 6
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 60.28512191772461,
      "learning_rate": 0.00014,
      "loss": 11.9511,
      "step": 7
    },
    {
      "epoch": 0.013061224489795919,
      "grad_norm": 7.907532215118408,
      "learning_rate": 0.00016,
      "loss": 10.4593,
      "step": 8
    },
    {
      "epoch": 0.014693877551020407,
      "grad_norm": 2.312899589538574,
      "learning_rate": 0.00018,
      "loss": 10.434,
      "step": 9
    },
    {
      "epoch": 0.014693877551020407,
      "eval_loss": 2.4650332927703857,
      "eval_runtime": 16.8309,
      "eval_samples_per_second": 15.329,
      "eval_steps_per_second": 7.664,
      "step": 9
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": 1.956859827041626,
      "learning_rate": 0.0002,
      "loss": 9.5035,
      "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": 2880780805570560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}