{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1841620626151013,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003683241252302026,
      "eval_loss": 5.5910258293151855,
      "eval_runtime": 7.7583,
      "eval_samples_per_second": 14.823,
      "eval_steps_per_second": 7.476,
      "step": 1
    },
    {
      "epoch": 0.01841620626151013,
      "grad_norm": 5.7768144607543945,
      "learning_rate": 5e-05,
      "loss": 5.2762,
      "step": 5
    },
    {
      "epoch": 0.03683241252302026,
      "grad_norm": 5.878540992736816,
      "learning_rate": 0.0001,
      "loss": 5.0933,
      "step": 10
    },
    {
      "epoch": 0.03683241252302026,
      "eval_loss": 4.4217329025268555,
      "eval_runtime": 7.7998,
      "eval_samples_per_second": 14.744,
      "eval_steps_per_second": 7.436,
      "step": 10
    },
    {
      "epoch": 0.055248618784530384,
      "grad_norm": 4.081850528717041,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.8333,
      "step": 15
    },
    {
      "epoch": 0.07366482504604052,
      "grad_norm": 3.7793331146240234,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.4672,
      "step": 20
    },
    {
      "epoch": 0.07366482504604052,
      "eval_loss": 3.481849431991577,
      "eval_runtime": 7.8167,
      "eval_samples_per_second": 14.712,
      "eval_steps_per_second": 7.42,
      "step": 20
    },
    {
      "epoch": 0.09208103130755065,
      "grad_norm": 3.1750733852386475,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.3337,
      "step": 25
    },
    {
      "epoch": 0.11049723756906077,
      "grad_norm": 2.7841458320617676,
      "learning_rate": 5e-05,
      "loss": 3.1313,
      "step": 30
    },
    {
      "epoch": 0.11049723756906077,
      "eval_loss": 3.438715934753418,
      "eval_runtime": 7.9289,
      "eval_samples_per_second": 14.504,
      "eval_steps_per_second": 7.315,
      "step": 30
    },
    {
      "epoch": 0.1289134438305709,
      "grad_norm": 3.650259256362915,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.2775,
      "step": 35
    },
    {
      "epoch": 0.14732965009208104,
      "grad_norm": 3.0431721210479736,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.2642,
      "step": 40
    },
    {
      "epoch": 0.14732965009208104,
      "eval_loss": 3.4098873138427734,
      "eval_runtime": 7.9272,
      "eval_samples_per_second": 14.507,
      "eval_steps_per_second": 7.317,
      "step": 40
    },
    {
      "epoch": 0.16574585635359115,
      "grad_norm": 3.3123347759246826,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.3549,
      "step": 45
    },
    {
      "epoch": 0.1841620626151013,
      "grad_norm": 2.9409520626068115,
      "learning_rate": 0.0,
      "loss": 3.2574,
      "step": 50
    },
    {
      "epoch": 0.1841620626151013,
      "eval_loss": 3.400886297225952,
      "eval_runtime": 7.8511,
      "eval_samples_per_second": 14.648,
      "eval_steps_per_second": 7.387,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}