{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05362469417166605,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005362469417166605,
      "grad_norm": 0.050072263926267624,
      "learning_rate": 1.4961796246648793e-05,
      "loss": 1.0673207283020019,
      "step": 20
    },
    {
      "epoch": 0.01072493883433321,
      "grad_norm": 0.06825340539216995,
      "learning_rate": 1.4921581769436997e-05,
      "loss": 0.9185627937316895,
      "step": 40
    },
    {
      "epoch": 0.016087408251499815,
      "grad_norm": 0.06827432662248611,
      "learning_rate": 1.48813672922252e-05,
      "loss": 0.7999343872070312,
      "step": 60
    },
    {
      "epoch": 0.02144987766866642,
      "grad_norm": 0.05807405710220337,
      "learning_rate": 1.4841152815013404e-05,
      "loss": 0.7322770595550537,
      "step": 80
    },
    {
      "epoch": 0.026812347085833025,
      "grad_norm": 0.06654328852891922,
      "learning_rate": 1.4800938337801608e-05,
      "loss": 0.7097890377044678,
      "step": 100
    },
    {
      "epoch": 0.03217481650299963,
      "grad_norm": 0.09104783087968826,
      "learning_rate": 1.4760723860589812e-05,
      "loss": 0.6513629913330078,
      "step": 120
    },
    {
      "epoch": 0.03753728592016624,
      "grad_norm": 0.10718850791454315,
      "learning_rate": 1.4720509383378015e-05,
      "loss": 0.678717851638794,
      "step": 140
    },
    {
      "epoch": 0.04289975533733284,
      "grad_norm": 0.09187154471874237,
      "learning_rate": 1.4680294906166219e-05,
      "loss": 0.647278118133545,
      "step": 160
    },
    {
      "epoch": 0.04826222475449945,
      "grad_norm": 0.07148946076631546,
      "learning_rate": 1.4640080428954423e-05,
      "loss": 0.6737877368927002,
      "step": 180
    },
    {
      "epoch": 0.05362469417166605,
      "grad_norm": 0.08909227699041367,
      "learning_rate": 1.4599865951742626e-05,
      "loss": 0.6373191356658936,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 7460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.461979015351501e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}