{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017250301880282905,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003450060376056581,
      "eval_loss": 1.9688220024108887,
      "eval_runtime": 81.235,
      "eval_samples_per_second": 15.03,
      "eval_steps_per_second": 7.521,
      "step": 1
    },
    {
      "epoch": 0.0017250301880282904,
      "grad_norm": 5.527597904205322,
      "learning_rate": 5e-05,
      "loss": 1.901,
      "step": 5
    },
    {
      "epoch": 0.003450060376056581,
      "grad_norm": 2.9979825019836426,
      "learning_rate": 0.0001,
      "loss": 1.374,
      "step": 10
    },
    {
      "epoch": 0.003450060376056581,
      "eval_loss": 1.1795198917388916,
      "eval_runtime": 81.7617,
      "eval_samples_per_second": 14.934,
      "eval_steps_per_second": 7.473,
      "step": 10
    },
    {
      "epoch": 0.005175090564084871,
      "grad_norm": 2.2583820819854736,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9523,
      "step": 15
    },
    {
      "epoch": 0.006900120752113162,
      "grad_norm": 2.296994686126709,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.884,
      "step": 20
    },
    {
      "epoch": 0.006900120752113162,
      "eval_loss": 0.6531204581260681,
      "eval_runtime": 81.8091,
      "eval_samples_per_second": 14.925,
      "eval_steps_per_second": 7.469,
      "step": 20
    },
    {
      "epoch": 0.008625150940141452,
      "grad_norm": 2.0689282417297363,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.634,
      "step": 25
    },
    {
      "epoch": 0.010350181128169742,
      "grad_norm": 1.740796446800232,
      "learning_rate": 5e-05,
      "loss": 0.4755,
      "step": 30
    },
    {
      "epoch": 0.010350181128169742,
      "eval_loss": 0.5024950504302979,
      "eval_runtime": 81.8931,
      "eval_samples_per_second": 14.91,
      "eval_steps_per_second": 7.461,
      "step": 30
    },
    {
      "epoch": 0.012075211316198034,
      "grad_norm": 1.8068922758102417,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.721,
      "step": 35
    },
    {
      "epoch": 0.013800241504226323,
      "grad_norm": 1.2980700731277466,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4492,
      "step": 40
    },
    {
      "epoch": 0.013800241504226323,
      "eval_loss": 0.4763771593570709,
      "eval_runtime": 81.9288,
      "eval_samples_per_second": 14.903,
      "eval_steps_per_second": 7.458,
      "step": 40
    },
    {
      "epoch": 0.015525271692254615,
      "grad_norm": 1.6496080160140991,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.4418,
      "step": 45
    },
    {
      "epoch": 0.017250301880282905,
      "grad_norm": 1.5776127576828003,
      "learning_rate": 0.0,
      "loss": 0.5057,
      "step": 50
    },
    {
      "epoch": 0.017250301880282905,
      "eval_loss": 0.47041645646095276,
      "eval_runtime": 82.0824,
      "eval_samples_per_second": 14.875,
      "eval_steps_per_second": 7.444,
      "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": 4894777933824000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}