{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017792011386887287,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.930670462295763e-05,
      "eval_loss": 12.147173881530762,
      "eval_runtime": 290.7949,
      "eval_samples_per_second": 24.416,
      "eval_steps_per_second": 12.208,
      "step": 1
    },
    {
      "epoch": 0.00017792011386887289,
      "grad_norm": 11.14660930633545,
      "learning_rate": 6e-05,
      "loss": 12.1674,
      "step": 3
    },
    {
      "epoch": 0.0002965335231147881,
      "eval_loss": 11.853402137756348,
      "eval_runtime": 294.1314,
      "eval_samples_per_second": 24.139,
      "eval_steps_per_second": 12.069,
      "step": 5
    },
    {
      "epoch": 0.00035584022773774577,
      "grad_norm": 10.97592830657959,
      "learning_rate": 0.00012,
      "loss": 11.9565,
      "step": 6
    },
    {
      "epoch": 0.0005337603416066186,
      "grad_norm": 8.313521385192871,
      "learning_rate": 0.00018,
      "loss": 11.4876,
      "step": 9
    },
    {
      "epoch": 0.0005930670462295762,
      "eval_loss": 10.954883575439453,
      "eval_runtime": 291.2838,
      "eval_samples_per_second": 24.375,
      "eval_steps_per_second": 12.187,
      "step": 10
    },
    {
      "epoch": 0.0007116804554754915,
      "grad_norm": 7.10131311416626,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.9684,
      "step": 12
    },
    {
      "epoch": 0.0008896005693443643,
      "grad_norm": 5.987206935882568,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.4647,
      "step": 15
    },
    {
      "epoch": 0.0008896005693443643,
      "eval_loss": 10.177637100219727,
      "eval_runtime": 294.0051,
      "eval_samples_per_second": 24.149,
      "eval_steps_per_second": 12.075,
      "step": 15
    },
    {
      "epoch": 0.0010675206832132373,
      "grad_norm": 5.192551612854004,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.0547,
      "step": 18
    },
    {
      "epoch": 0.0011861340924591525,
      "eval_loss": 9.714789390563965,
      "eval_runtime": 292.8811,
      "eval_samples_per_second": 24.242,
      "eval_steps_per_second": 12.121,
      "step": 20
    },
    {
      "epoch": 0.0012454407970821102,
      "grad_norm": 4.78351354598999,
      "learning_rate": 8.435655349597689e-05,
      "loss": 9.7974,
      "step": 21
    },
    {
      "epoch": 0.001423360910950983,
      "grad_norm": 4.210782527923584,
      "learning_rate": 4.12214747707527e-05,
      "loss": 9.623,
      "step": 24
    },
    {
      "epoch": 0.0014826676155739406,
      "eval_loss": 9.522984504699707,
      "eval_runtime": 293.8342,
      "eval_samples_per_second": 24.163,
      "eval_steps_per_second": 12.082,
      "step": 25
    },
    {
      "epoch": 0.0016012810248198558,
      "grad_norm": 3.7491424083709717,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 9.5269,
      "step": 27
    },
    {
      "epoch": 0.0017792011386887287,
      "grad_norm": 3.693744421005249,
      "learning_rate": 0.0,
      "loss": 9.4953,
      "step": 30
    },
    {
      "epoch": 0.0017792011386887287,
      "eval_loss": 9.486776351928711,
      "eval_runtime": 293.7624,
      "eval_samples_per_second": 24.169,
      "eval_steps_per_second": 12.085,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7771550121984.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}