{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009720723610665578,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9441447221331154e-05,
      "eval_loss": 2.7445335388183594,
      "eval_runtime": 1368.8069,
      "eval_samples_per_second": 15.823,
      "eval_steps_per_second": 7.911,
      "step": 1
    },
    {
      "epoch": 9.720723610665579e-05,
      "grad_norm": 0.9237040281295776,
      "learning_rate": 5e-05,
      "loss": 2.3938,
      "step": 5
    },
    {
      "epoch": 0.00019441447221331157,
      "grad_norm": 1.7170302867889404,
      "learning_rate": 0.0001,
      "loss": 2.3891,
      "step": 10
    },
    {
      "epoch": 0.00019441447221331157,
      "eval_loss": 2.664992332458496,
      "eval_runtime": 1377.1742,
      "eval_samples_per_second": 15.726,
      "eval_steps_per_second": 7.863,
      "step": 10
    },
    {
      "epoch": 0.00029162170831996734,
      "grad_norm": 1.593088984489441,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1917,
      "step": 15
    },
    {
      "epoch": 0.00038882894442662314,
      "grad_norm": 0.9290578961372375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.0063,
      "step": 20
    },
    {
      "epoch": 0.00038882894442662314,
      "eval_loss": 2.424437999725342,
      "eval_runtime": 1379.8073,
      "eval_samples_per_second": 15.696,
      "eval_steps_per_second": 7.848,
      "step": 20
    },
    {
      "epoch": 0.0004860361805332789,
      "grad_norm": 0.5730593800544739,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8733,
      "step": 25
    },
    {
      "epoch": 0.0005832434166399347,
      "grad_norm": 0.495732843875885,
      "learning_rate": 5e-05,
      "loss": 1.7655,
      "step": 30
    },
    {
      "epoch": 0.0005832434166399347,
      "eval_loss": 2.3357584476470947,
      "eval_runtime": 1379.2779,
      "eval_samples_per_second": 15.702,
      "eval_steps_per_second": 7.851,
      "step": 30
    },
    {
      "epoch": 0.0006804506527465905,
      "grad_norm": 0.6865149736404419,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8186,
      "step": 35
    },
    {
      "epoch": 0.0007776578888532463,
      "grad_norm": 0.8082664608955383,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0096,
      "step": 40
    },
    {
      "epoch": 0.0007776578888532463,
      "eval_loss": 2.290860891342163,
      "eval_runtime": 1374.3049,
      "eval_samples_per_second": 15.759,
      "eval_steps_per_second": 7.88,
      "step": 40
    },
    {
      "epoch": 0.000874865124959902,
      "grad_norm": 1.0085279941558838,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.9027,
      "step": 45
    },
    {
      "epoch": 0.0009720723610665578,
      "grad_norm": 0.7571061253547668,
      "learning_rate": 0.0,
      "loss": 2.009,
      "step": 50
    },
    {
      "epoch": 0.0009720723610665578,
      "eval_loss": 2.2849345207214355,
      "eval_runtime": 1378.3063,
      "eval_samples_per_second": 15.713,
      "eval_steps_per_second": 7.857,
      "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": 9202342217908224.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}