{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019271948608137045,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021413276231263384,
      "grad_norm": 11.087787628173828,
      "learning_rate": 2e-05,
      "loss": 5.3203,
      "step": 1
    },
    {
      "epoch": 0.0021413276231263384,
      "eval_loss": 1.3692880868911743,
      "eval_runtime": 9.9478,
      "eval_samples_per_second": 19.803,
      "eval_steps_per_second": 9.952,
      "step": 1
    },
    {
      "epoch": 0.004282655246252677,
      "grad_norm": 11.034947395324707,
      "learning_rate": 4e-05,
      "loss": 6.1669,
      "step": 2
    },
    {
      "epoch": 0.006423982869379015,
      "grad_norm": 9.019002914428711,
      "learning_rate": 6e-05,
      "loss": 5.6432,
      "step": 3
    },
    {
      "epoch": 0.006423982869379015,
      "eval_loss": 1.3476243019104004,
      "eval_runtime": 8.1048,
      "eval_samples_per_second": 24.307,
      "eval_steps_per_second": 12.215,
      "step": 3
    },
    {
      "epoch": 0.008565310492505354,
      "grad_norm": 6.628561973571777,
      "learning_rate": 8e-05,
      "loss": 5.4239,
      "step": 4
    },
    {
      "epoch": 0.010706638115631691,
      "grad_norm": 11.71303939819336,
      "learning_rate": 0.0001,
      "loss": 6.3184,
      "step": 5
    },
    {
      "epoch": 0.01284796573875803,
      "grad_norm": 7.048206329345703,
      "learning_rate": 0.00012,
      "loss": 4.3836,
      "step": 6
    },
    {
      "epoch": 0.01284796573875803,
      "eval_loss": 1.2384220361709595,
      "eval_runtime": 8.1702,
      "eval_samples_per_second": 24.112,
      "eval_steps_per_second": 12.117,
      "step": 6
    },
    {
      "epoch": 0.014989293361884369,
      "grad_norm": 8.569844245910645,
      "learning_rate": 0.00014,
      "loss": 5.2315,
      "step": 7
    },
    {
      "epoch": 0.017130620985010708,
      "grad_norm": 5.71522855758667,
      "learning_rate": 0.00016,
      "loss": 4.9675,
      "step": 8
    },
    {
      "epoch": 0.019271948608137045,
      "grad_norm": 6.9149298667907715,
      "learning_rate": 0.00018,
      "loss": 5.0579,
      "step": 9
    },
    {
      "epoch": 0.019271948608137045,
      "eval_loss": 1.174412488937378,
      "eval_runtime": 8.1316,
      "eval_samples_per_second": 24.227,
      "eval_steps_per_second": 12.175,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2147021720911872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}