{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014245014245014246,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014245014245014244,
      "grad_norm": 101.0147705078125,
      "learning_rate": 2e-05,
      "loss": 13.1573,
      "step": 1
    },
    {
      "epoch": 0.00014245014245014244,
      "eval_loss": 3.1389527320861816,
      "eval_runtime": 202.6348,
      "eval_samples_per_second": 14.588,
      "eval_steps_per_second": 7.294,
      "step": 1
    },
    {
      "epoch": 0.0002849002849002849,
      "grad_norm": 44.48573303222656,
      "learning_rate": 4e-05,
      "loss": 10.7486,
      "step": 2
    },
    {
      "epoch": 0.00042735042735042735,
      "grad_norm": 36.15799331665039,
      "learning_rate": 6e-05,
      "loss": 12.5112,
      "step": 3
    },
    {
      "epoch": 0.00042735042735042735,
      "eval_loss": 3.075819730758667,
      "eval_runtime": 202.487,
      "eval_samples_per_second": 14.598,
      "eval_steps_per_second": 7.299,
      "step": 3
    },
    {
      "epoch": 0.0005698005698005698,
      "grad_norm": 38.643619537353516,
      "learning_rate": 8e-05,
      "loss": 12.385,
      "step": 4
    },
    {
      "epoch": 0.0007122507122507123,
      "grad_norm": 83.11431121826172,
      "learning_rate": 0.0001,
      "loss": 13.1583,
      "step": 5
    },
    {
      "epoch": 0.0008547008547008547,
      "grad_norm": 43.42289733886719,
      "learning_rate": 0.00012,
      "loss": 10.9983,
      "step": 6
    },
    {
      "epoch": 0.0008547008547008547,
      "eval_loss": 2.512888193130493,
      "eval_runtime": 202.3879,
      "eval_samples_per_second": 14.606,
      "eval_steps_per_second": 7.303,
      "step": 6
    },
    {
      "epoch": 0.0009971509971509972,
      "grad_norm": 154.86273193359375,
      "learning_rate": 0.00014,
      "loss": 11.057,
      "step": 7
    },
    {
      "epoch": 0.0011396011396011395,
      "grad_norm": 38.27873229980469,
      "learning_rate": 0.00016,
      "loss": 10.6012,
      "step": 8
    },
    {
      "epoch": 0.001282051282051282,
      "grad_norm": 43.07347869873047,
      "learning_rate": 0.00018,
      "loss": 12.0841,
      "step": 9
    },
    {
      "epoch": 0.001282051282051282,
      "eval_loss": 2.084683418273926,
      "eval_runtime": 202.642,
      "eval_samples_per_second": 14.587,
      "eval_steps_per_second": 7.294,
      "step": 9
    },
    {
      "epoch": 0.0014245014245014246,
      "grad_norm": 29.965913772583008,
      "learning_rate": 0.0002,
      "loss": 9.2473,
      "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": 3505339571896320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}