{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003658380434981434,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.316760869962868e-05,
      "eval_loss": 1.0180927515029907,
      "eval_runtime": 246.1512,
      "eval_samples_per_second": 23.38,
      "eval_steps_per_second": 11.692,
      "step": 1
    },
    {
      "epoch": 0.00036583804349814335,
      "grad_norm": 3.355719804763794,
      "learning_rate": 5e-05,
      "loss": 0.856,
      "step": 5
    },
    {
      "epoch": 0.0007316760869962867,
      "grad_norm": 1.5776859521865845,
      "learning_rate": 0.0001,
      "loss": 0.6334,
      "step": 10
    },
    {
      "epoch": 0.0007316760869962867,
      "eval_loss": 0.40519312024116516,
      "eval_runtime": 245.4313,
      "eval_samples_per_second": 23.449,
      "eval_steps_per_second": 11.726,
      "step": 10
    },
    {
      "epoch": 0.00109751413049443,
      "grad_norm": 1.2322691679000854,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2074,
      "step": 15
    },
    {
      "epoch": 0.0014633521739925734,
      "grad_norm": 0.9002659320831299,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0406,
      "step": 20
    },
    {
      "epoch": 0.0014633521739925734,
      "eval_loss": 0.02797255851328373,
      "eval_runtime": 244.23,
      "eval_samples_per_second": 23.564,
      "eval_steps_per_second": 11.784,
      "step": 20
    },
    {
      "epoch": 0.001829190217490717,
      "grad_norm": 0.5813238024711609,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0415,
      "step": 25
    },
    {
      "epoch": 0.00219502826098886,
      "grad_norm": 0.4815821051597595,
      "learning_rate": 5e-05,
      "loss": 0.0249,
      "step": 30
    },
    {
      "epoch": 0.00219502826098886,
      "eval_loss": 0.0143667533993721,
      "eval_runtime": 245.4483,
      "eval_samples_per_second": 23.447,
      "eval_steps_per_second": 11.725,
      "step": 30
    },
    {
      "epoch": 0.0025608663044870035,
      "grad_norm": 1.179526448249817,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0057,
      "step": 35
    },
    {
      "epoch": 0.002926704347985147,
      "grad_norm": 0.06061702221632004,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0142,
      "step": 40
    },
    {
      "epoch": 0.002926704347985147,
      "eval_loss": 0.012320216745138168,
      "eval_runtime": 247.6998,
      "eval_samples_per_second": 23.234,
      "eval_steps_per_second": 11.619,
      "step": 40
    },
    {
      "epoch": 0.0032925423914832905,
      "grad_norm": 0.14113092422485352,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0161,
      "step": 45
    },
    {
      "epoch": 0.003658380434981434,
      "grad_norm": 0.19074559211730957,
      "learning_rate": 0.0,
      "loss": 0.0039,
      "step": 50
    },
    {
      "epoch": 0.003658380434981434,
      "eval_loss": 0.011827120557427406,
      "eval_runtime": 246.9835,
      "eval_samples_per_second": 23.301,
      "eval_steps_per_second": 11.653,
      "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": 2973577594798080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}