{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008133718329334256,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001626743665866851,
      "eval_loss": NaN,
      "eval_runtime": 125.1033,
      "eval_samples_per_second": 20.695,
      "eval_steps_per_second": 10.351,
      "step": 1
    },
    {
      "epoch": 0.0008133718329334255,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.001626743665866851,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.001626743665866851,
      "eval_loss": NaN,
      "eval_runtime": 124.1419,
      "eval_samples_per_second": 20.855,
      "eval_steps_per_second": 10.432,
      "step": 10
    },
    {
      "epoch": 0.0024401154988002763,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.003253487331733702,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.003253487331733702,
      "eval_loss": NaN,
      "eval_runtime": 137.9667,
      "eval_samples_per_second": 18.765,
      "eval_steps_per_second": 9.386,
      "step": 20
    },
    {
      "epoch": 0.004066859164667128,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.004880230997600553,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.004880230997600553,
      "eval_loss": NaN,
      "eval_runtime": 140.3471,
      "eval_samples_per_second": 18.447,
      "eval_steps_per_second": 9.227,
      "step": 30
    },
    {
      "epoch": 0.005693602830533978,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.006506974663467404,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.006506974663467404,
      "eval_loss": NaN,
      "eval_runtime": 131.2723,
      "eval_samples_per_second": 19.722,
      "eval_steps_per_second": 9.865,
      "step": 40
    },
    {
      "epoch": 0.0073203464964008294,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.008133718329334256,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.008133718329334256,
      "eval_loss": NaN,
      "eval_runtime": 124.5274,
      "eval_samples_per_second": 20.791,
      "eval_steps_per_second": 10.399,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3428033180467200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}