{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0025356370788160525,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.501633535425775e-05,
      "eval_loss": 6.663437843322754,
      "eval_runtime": 77.4622,
      "eval_samples_per_second": 83.615,
      "eval_steps_per_second": 41.814,
      "step": 1
    },
    {
      "epoch": 0.00032508167677128876,
      "grad_norm": 3.2935903072357178,
      "learning_rate": 5e-05,
      "loss": 6.4505,
      "step": 5
    },
    {
      "epoch": 0.0006501633535425775,
      "grad_norm": 2.8207027912139893,
      "learning_rate": 0.0001,
      "loss": 6.6583,
      "step": 10
    },
    {
      "epoch": 0.0006501633535425775,
      "eval_loss": 6.633432388305664,
      "eval_runtime": 76.7926,
      "eval_samples_per_second": 84.344,
      "eval_steps_per_second": 42.179,
      "step": 10
    },
    {
      "epoch": 0.0009752450303138663,
      "grad_norm": 2.793973445892334,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.6605,
      "step": 15
    },
    {
      "epoch": 0.001300326707085155,
      "grad_norm": 2.789121389389038,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.4801,
      "step": 20
    },
    {
      "epoch": 0.001300326707085155,
      "eval_loss": 6.546636581420898,
      "eval_runtime": 76.8222,
      "eval_samples_per_second": 84.312,
      "eval_steps_per_second": 42.162,
      "step": 20
    },
    {
      "epoch": 0.0016254083838564439,
      "grad_norm": 2.7600698471069336,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.5366,
      "step": 25
    },
    {
      "epoch": 0.0019504900606277327,
      "grad_norm": 3.074209213256836,
      "learning_rate": 5e-05,
      "loss": 6.3263,
      "step": 30
    },
    {
      "epoch": 0.0019504900606277327,
      "eval_loss": 6.492212772369385,
      "eval_runtime": 77.4723,
      "eval_samples_per_second": 83.604,
      "eval_steps_per_second": 41.808,
      "step": 30
    },
    {
      "epoch": 0.0022755717373990213,
      "grad_norm": 2.571615219116211,
      "learning_rate": 3.086582838174551e-05,
      "loss": 6.5978,
      "step": 35
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5031618281472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}