{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05324813631522897,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010649627263045794,
      "eval_loss": 0.9507185816764832,
      "eval_runtime": 58.3439,
      "eval_samples_per_second": 6.787,
      "eval_steps_per_second": 3.394,
      "step": 1
    },
    {
      "epoch": 0.005324813631522897,
      "grad_norm": 10.506938934326172,
      "learning_rate": 5e-05,
      "loss": 3.216,
      "step": 5
    },
    {
      "epoch": 0.010649627263045794,
      "grad_norm": 7.601571083068848,
      "learning_rate": 0.0001,
      "loss": 3.7606,
      "step": 10
    },
    {
      "epoch": 0.010649627263045794,
      "eval_loss": 0.8951508402824402,
      "eval_runtime": 58.9447,
      "eval_samples_per_second": 6.718,
      "eval_steps_per_second": 3.359,
      "step": 10
    },
    {
      "epoch": 0.01597444089456869,
      "grad_norm": 8.849002838134766,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.4523,
      "step": 15
    },
    {
      "epoch": 0.021299254526091587,
      "grad_norm": 10.705131530761719,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.2362,
      "step": 20
    },
    {
      "epoch": 0.021299254526091587,
      "eval_loss": 0.8569461703300476,
      "eval_runtime": 59.0108,
      "eval_samples_per_second": 6.711,
      "eval_steps_per_second": 3.355,
      "step": 20
    },
    {
      "epoch": 0.026624068157614485,
      "grad_norm": 7.336248874664307,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.3764,
      "step": 25
    },
    {
      "epoch": 0.03194888178913738,
      "grad_norm": 6.142819404602051,
      "learning_rate": 5e-05,
      "loss": 3.0118,
      "step": 30
    },
    {
      "epoch": 0.03194888178913738,
      "eval_loss": 0.8355762958526611,
      "eval_runtime": 58.9546,
      "eval_samples_per_second": 6.717,
      "eval_steps_per_second": 3.359,
      "step": 30
    },
    {
      "epoch": 0.03727369542066028,
      "grad_norm": 6.7355804443359375,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.6674,
      "step": 35
    },
    {
      "epoch": 0.042598509052183174,
      "grad_norm": 6.555343151092529,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.1935,
      "step": 40
    },
    {
      "epoch": 0.042598509052183174,
      "eval_loss": 0.8272697329521179,
      "eval_runtime": 58.9776,
      "eval_samples_per_second": 6.714,
      "eval_steps_per_second": 3.357,
      "step": 40
    },
    {
      "epoch": 0.04792332268370607,
      "grad_norm": 5.486558437347412,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.4542,
      "step": 45
    },
    {
      "epoch": 0.05324813631522897,
      "grad_norm": 5.475861072540283,
      "learning_rate": 0.0,
      "loss": 2.8325,
      "step": 50
    },
    {
      "epoch": 0.05324813631522897,
      "eval_loss": 0.8255319595336914,
      "eval_runtime": 59.0817,
      "eval_samples_per_second": 6.703,
      "eval_steps_per_second": 3.351,
      "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": 1.6475095987912704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}