{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25296442687747034,
  "eval_steps": 16,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015810276679841896,
      "grad_norm": 3.106086254119873,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2762,
      "step": 1
    },
    {
      "epoch": 0.015810276679841896,
      "eval_loss": 0.34248441457748413,
      "eval_runtime": 9.4978,
      "eval_samples_per_second": 11.266,
      "eval_steps_per_second": 2.843,
      "step": 1
    },
    {
      "epoch": 0.03162055335968379,
      "grad_norm": 0.6217677593231201,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2623,
      "step": 2
    },
    {
      "epoch": 0.04743083003952569,
      "grad_norm": 1.1419365406036377,
      "learning_rate": 6e-06,
      "loss": 0.3943,
      "step": 3
    },
    {
      "epoch": 0.06324110671936758,
      "grad_norm": 0.8881447315216064,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1572,
      "step": 4
    },
    {
      "epoch": 0.07905138339920949,
      "grad_norm": 0.7020868062973022,
      "learning_rate": 1e-05,
      "loss": 0.1578,
      "step": 5
    },
    {
      "epoch": 0.09486166007905138,
      "grad_norm": 1.2612448930740356,
      "learning_rate": 1.2e-05,
      "loss": 0.2245,
      "step": 6
    },
    {
      "epoch": 0.11067193675889328,
      "grad_norm": 1.2954490184783936,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.2101,
      "step": 7
    },
    {
      "epoch": 0.12648221343873517,
      "grad_norm": 0.8434045314788818,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1529,
      "step": 8
    },
    {
      "epoch": 0.1422924901185771,
      "grad_norm": 0.9214808940887451,
      "learning_rate": 1.8e-05,
      "loss": 0.1522,
      "step": 9
    },
    {
      "epoch": 0.15810276679841898,
      "grad_norm": 1.3638683557510376,
      "learning_rate": 2e-05,
      "loss": 0.3282,
      "step": 10
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 2.2487895488739014,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.472,
      "step": 11
    },
    {
      "epoch": 0.18972332015810275,
      "grad_norm": 1.98398756980896,
      "learning_rate": 2.4e-05,
      "loss": 0.4099,
      "step": 12
    },
    {
      "epoch": 0.20553359683794467,
      "grad_norm": 1.796846866607666,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.3184,
      "step": 13
    },
    {
      "epoch": 0.22134387351778656,
      "grad_norm": 1.6363037824630737,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.3551,
      "step": 14
    },
    {
      "epoch": 0.23715415019762845,
      "grad_norm": 1.927720308303833,
      "learning_rate": 3e-05,
      "loss": 0.405,
      "step": 15
    },
    {
      "epoch": 0.25296442687747034,
      "grad_norm": 1.0266072750091553,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2991,
      "step": 16
    },
    {
      "epoch": 0.25296442687747034,
      "eval_loss": 0.21815715730190277,
      "eval_runtime": 8.042,
      "eval_samples_per_second": 13.305,
      "eval_steps_per_second": 3.357,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2383975687389184.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}