{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.022629554197782304,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045259108395564606,
      "eval_loss": 0.4409753978252411,
      "eval_runtime": 118.7119,
      "eval_samples_per_second": 7.843,
      "eval_steps_per_second": 3.925,
      "step": 1
    },
    {
      "epoch": 0.0022629554197782305,
      "grad_norm": 0.29531562328338623,
      "learning_rate": 5e-05,
      "loss": 0.4614,
      "step": 5
    },
    {
      "epoch": 0.004525910839556461,
      "grad_norm": 0.378474622964859,
      "learning_rate": 0.0001,
      "loss": 0.4523,
      "step": 10
    },
    {
      "epoch": 0.004525910839556461,
      "eval_loss": 0.4033299386501312,
      "eval_runtime": 119.6018,
      "eval_samples_per_second": 7.784,
      "eval_steps_per_second": 3.896,
      "step": 10
    },
    {
      "epoch": 0.006788866259334691,
      "grad_norm": 0.3956564664840698,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3769,
      "step": 15
    },
    {
      "epoch": 0.009051821679112922,
      "grad_norm": 0.3755531907081604,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3542,
      "step": 20
    },
    {
      "epoch": 0.009051821679112922,
      "eval_loss": 0.3478148281574249,
      "eval_runtime": 120.1788,
      "eval_samples_per_second": 7.747,
      "eval_steps_per_second": 3.878,
      "step": 20
    },
    {
      "epoch": 0.011314777098891152,
      "grad_norm": 0.302672803401947,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3068,
      "step": 25
    },
    {
      "epoch": 0.013577732518669382,
      "grad_norm": 0.38788050413131714,
      "learning_rate": 5e-05,
      "loss": 0.3843,
      "step": 30
    },
    {
      "epoch": 0.013577732518669382,
      "eval_loss": 0.32981234788894653,
      "eval_runtime": 120.5023,
      "eval_samples_per_second": 7.726,
      "eval_steps_per_second": 3.867,
      "step": 30
    },
    {
      "epoch": 0.015840687938447614,
      "grad_norm": 0.39614132046699524,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.3411,
      "step": 35
    },
    {
      "epoch": 0.018103643358225844,
      "grad_norm": 0.3649158477783203,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2884,
      "step": 40
    },
    {
      "epoch": 0.018103643358225844,
      "eval_loss": 0.3227105140686035,
      "eval_runtime": 120.3902,
      "eval_samples_per_second": 7.733,
      "eval_steps_per_second": 3.871,
      "step": 40
    },
    {
      "epoch": 0.020366598778004074,
      "grad_norm": 0.35576507449150085,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3377,
      "step": 45
    },
    {
      "epoch": 0.022629554197782304,
      "grad_norm": 0.36561909317970276,
      "learning_rate": 0.0,
      "loss": 0.3536,
      "step": 50
    },
    {
      "epoch": 0.022629554197782304,
      "eval_loss": 0.32128387689590454,
      "eval_runtime": 119.4005,
      "eval_samples_per_second": 7.797,
      "eval_steps_per_second": 3.903,
      "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": 1.8171978628202496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}