{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013592832869941304,
  "eval_steps": 5,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004119040263618577,
      "eval_loss": NaN,
      "eval_runtime": 214.2249,
      "eval_samples_per_second": 4.775,
      "eval_steps_per_second": 2.39,
      "step": 1
    },
    {
      "epoch": 0.001235712079085573,
      "grad_norm": NaN,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0020595201318092883,
      "eval_loss": NaN,
      "eval_runtime": 214.3037,
      "eval_samples_per_second": 4.774,
      "eval_steps_per_second": 2.389,
      "step": 5
    },
    {
      "epoch": 0.002471424158171146,
      "grad_norm": NaN,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0037071362372567192,
      "grad_norm": NaN,
      "learning_rate": 0.00010588235294117647,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004119040263618577,
      "eval_loss": NaN,
      "eval_runtime": 214.1599,
      "eval_samples_per_second": 4.777,
      "eval_steps_per_second": 2.391,
      "step": 10
    },
    {
      "epoch": 0.004942848316342292,
      "grad_norm": NaN,
      "learning_rate": 0.0001411764705882353,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.006178560395427865,
      "grad_norm": NaN,
      "learning_rate": 0.00017647058823529413,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.006178560395427865,
      "eval_loss": NaN,
      "eval_runtime": 214.295,
      "eval_samples_per_second": 4.774,
      "eval_steps_per_second": 2.389,
      "step": 15
    },
    {
      "epoch": 0.0074142724745134385,
      "grad_norm": NaN,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.008238080527237153,
      "eval_loss": NaN,
      "eval_runtime": 214.2978,
      "eval_samples_per_second": 4.774,
      "eval_steps_per_second": 2.389,
      "step": 20
    },
    {
      "epoch": 0.008649984553599012,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.009885696632684585,
      "grad_norm": NaN,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.010297600659046443,
      "eval_loss": NaN,
      "eval_runtime": 214.2792,
      "eval_samples_per_second": 4.774,
      "eval_steps_per_second": 2.389,
      "step": 25
    },
    {
      "epoch": 0.011121408711770158,
      "grad_norm": NaN,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.01235712079085573,
      "grad_norm": NaN,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.01235712079085573,
      "eval_loss": NaN,
      "eval_runtime": 214.3212,
      "eval_samples_per_second": 4.773,
      "eval_steps_per_second": 2.389,
      "step": 30
    },
    {
      "epoch": 0.013592832869941304,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 33
    }
  ],
  "logging_steps": 3,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.332431526920192e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}