{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008438533720380747,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6877067440761493e-05,
      "eval_loss": 1.1438838243484497,
      "eval_runtime": 3846.8374,
      "eval_samples_per_second": 6.486,
      "eval_steps_per_second": 3.243,
      "step": 1
    },
    {
      "epoch": 8.438533720380746e-05,
      "grad_norm": 15.637603759765625,
      "learning_rate": 5e-05,
      "loss": 3.9254,
      "step": 5
    },
    {
      "epoch": 0.00016877067440761493,
      "grad_norm": 18.86083221435547,
      "learning_rate": 0.0001,
      "loss": 3.2658,
      "step": 10
    },
    {
      "epoch": 0.00016877067440761493,
      "eval_loss": 0.7776293158531189,
      "eval_runtime": 3848.324,
      "eval_samples_per_second": 6.483,
      "eval_steps_per_second": 3.242,
      "step": 10
    },
    {
      "epoch": 0.0002531560116114224,
      "grad_norm": 15.467984199523926,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.9974,
      "step": 15
    },
    {
      "epoch": 0.00033754134881522986,
      "grad_norm": 10.379603385925293,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1429,
      "step": 20
    },
    {
      "epoch": 0.00033754134881522986,
      "eval_loss": 0.48591312766075134,
      "eval_runtime": 3854.0801,
      "eval_samples_per_second": 6.473,
      "eval_steps_per_second": 3.237,
      "step": 20
    },
    {
      "epoch": 0.00042192668601903735,
      "grad_norm": 6.343555927276611,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8848,
      "step": 25
    },
    {
      "epoch": 0.0005063120232228448,
      "grad_norm": 6.2026143074035645,
      "learning_rate": 5e-05,
      "loss": 1.7887,
      "step": 30
    },
    {
      "epoch": 0.0005063120232228448,
      "eval_loss": 0.4375861585140228,
      "eval_runtime": 3847.7982,
      "eval_samples_per_second": 6.484,
      "eval_steps_per_second": 3.242,
      "step": 30
    },
    {
      "epoch": 0.0005906973604266522,
      "grad_norm": 10.28553295135498,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.7718,
      "step": 35
    },
    {
      "epoch": 0.0006750826976304597,
      "grad_norm": 15.07571792602539,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.6182,
      "step": 40
    },
    {
      "epoch": 0.0006750826976304597,
      "eval_loss": 0.4187605679035187,
      "eval_runtime": 3862.6805,
      "eval_samples_per_second": 6.459,
      "eval_steps_per_second": 3.23,
      "step": 40
    },
    {
      "epoch": 0.0007594680348342672,
      "grad_norm": 4.738510608673096,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5662,
      "step": 45
    },
    {
      "epoch": 0.0008438533720380747,
      "grad_norm": 6.462911605834961,
      "learning_rate": 0.0,
      "loss": 1.7484,
      "step": 50
    },
    {
      "epoch": 0.0008438533720380747,
      "eval_loss": 0.41282740235328674,
      "eval_runtime": 3861.9297,
      "eval_samples_per_second": 6.46,
      "eval_steps_per_second": 3.23,
      "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": 1.7439064370184192e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}