{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.35437430786268,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017718715393133997,
      "grad_norm": 0.1302589625120163,
      "learning_rate": 1e-05,
      "loss": 10.8316,
      "step": 1
    },
    {
      "epoch": 0.017718715393133997,
      "eval_loss": 10.837669372558594,
      "eval_runtime": 42.9982,
      "eval_samples_per_second": 2.209,
      "eval_steps_per_second": 1.116,
      "step": 1
    },
    {
      "epoch": 0.035437430786267994,
      "grad_norm": 0.1255638301372528,
      "learning_rate": 2e-05,
      "loss": 10.8358,
      "step": 2
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 0.11465005576610565,
      "learning_rate": 3e-05,
      "loss": 10.8346,
      "step": 3
    },
    {
      "epoch": 0.07087486157253599,
      "grad_norm": 0.12045992165803909,
      "learning_rate": 4e-05,
      "loss": 10.8343,
      "step": 4
    },
    {
      "epoch": 0.08859357696567,
      "grad_norm": 0.11077123880386353,
      "learning_rate": 5e-05,
      "loss": 10.8388,
      "step": 5
    },
    {
      "epoch": 0.08859357696567,
      "eval_loss": 10.837287902832031,
      "eval_runtime": 0.6589,
      "eval_samples_per_second": 144.169,
      "eval_steps_per_second": 72.843,
      "step": 5
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 0.12167657166719437,
      "learning_rate": 6e-05,
      "loss": 10.8354,
      "step": 6
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 0.11268478631973267,
      "learning_rate": 7e-05,
      "loss": 10.8366,
      "step": 7
    },
    {
      "epoch": 0.14174972314507198,
      "grad_norm": 0.1419811248779297,
      "learning_rate": 8e-05,
      "loss": 10.8329,
      "step": 8
    },
    {
      "epoch": 0.15946843853820597,
      "grad_norm": 0.11876291781663895,
      "learning_rate": 9e-05,
      "loss": 10.8353,
      "step": 9
    },
    {
      "epoch": 0.17718715393134,
      "grad_norm": 0.11256567388772964,
      "learning_rate": 0.0001,
      "loss": 10.8336,
      "step": 10
    },
    {
      "epoch": 0.17718715393134,
      "eval_loss": 10.83576488494873,
      "eval_runtime": 0.6028,
      "eval_samples_per_second": 157.588,
      "eval_steps_per_second": 79.623,
      "step": 10
    },
    {
      "epoch": 0.19490586932447398,
      "grad_norm": 0.12249582260847092,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.8356,
      "step": 11
    },
    {
      "epoch": 0.21262458471760798,
      "grad_norm": 0.13018162548542023,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.8313,
      "step": 12
    },
    {
      "epoch": 0.23034330011074197,
      "grad_norm": 0.11912107467651367,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.8301,
      "step": 13
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 0.11177022755146027,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.8316,
      "step": 14
    },
    {
      "epoch": 0.26578073089701,
      "grad_norm": 0.13372187316417694,
      "learning_rate": 5e-05,
      "loss": 10.8337,
      "step": 15
    },
    {
      "epoch": 0.26578073089701,
      "eval_loss": 10.833840370178223,
      "eval_runtime": 0.6893,
      "eval_samples_per_second": 137.818,
      "eval_steps_per_second": 69.635,
      "step": 15
    },
    {
      "epoch": 0.28349944629014395,
      "grad_norm": 0.12062043696641922,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.8331,
      "step": 16
    },
    {
      "epoch": 0.301218161683278,
      "grad_norm": 0.12629450857639313,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.837,
      "step": 17
    },
    {
      "epoch": 0.31893687707641194,
      "grad_norm": 0.13337388634681702,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.8319,
      "step": 18
    },
    {
      "epoch": 0.33665559246954596,
      "grad_norm": 0.12452352792024612,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.8309,
      "step": 19
    },
    {
      "epoch": 0.35437430786268,
      "grad_norm": 0.12699002027511597,
      "learning_rate": 0.0,
      "loss": 10.8314,
      "step": 20
    },
    {
      "epoch": 0.35437430786268,
      "eval_loss": 10.833288192749023,
      "eval_runtime": 0.6024,
      "eval_samples_per_second": 157.699,
      "eval_steps_per_second": 79.679,
      "step": 20
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6603380883456.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}