{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007416334476684898,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007416334476684898,
      "grad_norm": 11.244009017944336,
      "learning_rate": 2e-05,
      "loss": 18.8184,
      "step": 1
    },
    {
      "epoch": 0.0007416334476684898,
      "eval_loss": 2.656465768814087,
      "eval_runtime": 71.0748,
      "eval_samples_per_second": 7.992,
      "eval_steps_per_second": 7.992,
      "step": 1
    },
    {
      "epoch": 0.0014832668953369797,
      "grad_norm": 13.321176528930664,
      "learning_rate": 4e-05,
      "loss": 24.6349,
      "step": 2
    },
    {
      "epoch": 0.0022249003430054697,
      "grad_norm": 10.89687728881836,
      "learning_rate": 6e-05,
      "loss": 19.4295,
      "step": 3
    },
    {
      "epoch": 0.0029665337906739594,
      "grad_norm": 11.234940528869629,
      "learning_rate": 8e-05,
      "loss": 19.7558,
      "step": 4
    },
    {
      "epoch": 0.003708167238342449,
      "grad_norm": 15.064847946166992,
      "learning_rate": 0.0001,
      "loss": 20.2215,
      "step": 5
    },
    {
      "epoch": 0.003708167238342449,
      "eval_loss": 2.5815353393554688,
      "eval_runtime": 71.1425,
      "eval_samples_per_second": 7.984,
      "eval_steps_per_second": 7.984,
      "step": 5
    },
    {
      "epoch": 0.004449800686010939,
      "grad_norm": 15.631669998168945,
      "learning_rate": 0.00012,
      "loss": 19.749,
      "step": 6
    },
    {
      "epoch": 0.005191434133679429,
      "grad_norm": 22.724105834960938,
      "learning_rate": 0.00014,
      "loss": 17.047,
      "step": 7
    },
    {
      "epoch": 0.005933067581347919,
      "grad_norm": 18.232868194580078,
      "learning_rate": 0.00016,
      "loss": 19.128,
      "step": 8
    },
    {
      "epoch": 0.006674701029016409,
      "grad_norm": 26.458662033081055,
      "learning_rate": 0.00018,
      "loss": 20.2605,
      "step": 9
    },
    {
      "epoch": 0.007416334476684898,
      "grad_norm": 28.14463996887207,
      "learning_rate": 0.0002,
      "loss": 11.6753,
      "step": 10
    },
    {
      "epoch": 0.007416334476684898,
      "eval_loss": 1.3254823684692383,
      "eval_runtime": 71.3979,
      "eval_samples_per_second": 7.955,
      "eval_steps_per_second": 7.955,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 813146528808960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}