{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07911001236093942,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003955500618046972,
      "grad_norm": 66.62299346923828,
      "learning_rate": 1e-05,
      "loss": 128.6241,
      "step": 1
    },
    {
      "epoch": 0.003955500618046972,
      "eval_loss": 4.237987995147705,
      "eval_runtime": 307.5537,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 1
    },
    {
      "epoch": 0.007911001236093944,
      "grad_norm": 65.98905181884766,
      "learning_rate": 2e-05,
      "loss": 138.1243,
      "step": 2
    },
    {
      "epoch": 0.011866501854140914,
      "grad_norm": 68.6584243774414,
      "learning_rate": 3e-05,
      "loss": 136.2323,
      "step": 3
    },
    {
      "epoch": 0.015822002472187888,
      "grad_norm": 70.29867553710938,
      "learning_rate": 4e-05,
      "loss": 133.9982,
      "step": 4
    },
    {
      "epoch": 0.019777503090234856,
      "grad_norm": 67.28761291503906,
      "learning_rate": 5e-05,
      "loss": 129.0051,
      "step": 5
    },
    {
      "epoch": 0.019777503090234856,
      "eval_loss": 4.1191630363464355,
      "eval_runtime": 307.5897,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 5
    },
    {
      "epoch": 0.023733003708281828,
      "grad_norm": 78.57897186279297,
      "learning_rate": 6e-05,
      "loss": 144.2249,
      "step": 6
    },
    {
      "epoch": 0.0276885043263288,
      "grad_norm": 94.01433563232422,
      "learning_rate": 7e-05,
      "loss": 131.2312,
      "step": 7
    },
    {
      "epoch": 0.031644004944375775,
      "grad_norm": 93.0120620727539,
      "learning_rate": 8e-05,
      "loss": 114.7555,
      "step": 8
    },
    {
      "epoch": 0.035599505562422744,
      "grad_norm": 103.75362396240234,
      "learning_rate": 9e-05,
      "loss": 117.9606,
      "step": 9
    },
    {
      "epoch": 0.03955500618046971,
      "grad_norm": 101.03894805908203,
      "learning_rate": 0.0001,
      "loss": 109.0838,
      "step": 10
    },
    {
      "epoch": 0.03955500618046971,
      "eval_loss": 3.0349903106689453,
      "eval_runtime": 307.556,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 10
    },
    {
      "epoch": 0.04351050679851669,
      "grad_norm": 72.24517059326172,
      "learning_rate": 9.755282581475769e-05,
      "loss": 86.7828,
      "step": 11
    },
    {
      "epoch": 0.047466007416563656,
      "grad_norm": 75.16802215576172,
      "learning_rate": 9.045084971874738e-05,
      "loss": 90.0533,
      "step": 12
    },
    {
      "epoch": 0.05142150803461063,
      "grad_norm": 66.52326965332031,
      "learning_rate": 7.938926261462366e-05,
      "loss": 85.0806,
      "step": 13
    },
    {
      "epoch": 0.0553770086526576,
      "grad_norm": 68.9215316772461,
      "learning_rate": 6.545084971874738e-05,
      "loss": 77.0213,
      "step": 14
    },
    {
      "epoch": 0.059332509270704575,
      "grad_norm": 59.450138092041016,
      "learning_rate": 5e-05,
      "loss": 75.1714,
      "step": 15
    },
    {
      "epoch": 0.059332509270704575,
      "eval_loss": 2.192617893218994,
      "eval_runtime": 307.582,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 15
    },
    {
      "epoch": 0.06328800988875155,
      "grad_norm": 53.142982482910156,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 74.962,
      "step": 16
    },
    {
      "epoch": 0.06724351050679851,
      "grad_norm": 52.852928161621094,
      "learning_rate": 2.061073738537635e-05,
      "loss": 68.2094,
      "step": 17
    },
    {
      "epoch": 0.07119901112484549,
      "grad_norm": 48.375308990478516,
      "learning_rate": 9.549150281252633e-06,
      "loss": 67.8407,
      "step": 18
    },
    {
      "epoch": 0.07515451174289246,
      "grad_norm": 47.157535552978516,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 66.793,
      "step": 19
    },
    {
      "epoch": 0.07911001236093942,
      "grad_norm": 44.836360931396484,
      "learning_rate": 0.0,
      "loss": 63.8398,
      "step": 20
    },
    {
      "epoch": 0.07911001236093942,
      "eval_loss": 2.0867512226104736,
      "eval_runtime": 307.8872,
      "eval_samples_per_second": 2.767,
      "eval_steps_per_second": 1.384,
      "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": 2.0910662460899328e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}