{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025885276454752536,
  "eval_steps": 25,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0051770552909505075,
      "grad_norm": 6.5560479164123535,
      "learning_rate": 2.3797595190380762e-05,
      "loss": 2.3718,
      "step": 25
    },
    {
      "epoch": 0.0051770552909505075,
      "eval_loss": 2.1950066089630127,
      "eval_runtime": 22606.8976,
      "eval_samples_per_second": 0.427,
      "eval_steps_per_second": 0.053,
      "step": 25
    },
    {
      "epoch": 0.010354110581901015,
      "grad_norm": 6.057673454284668,
      "learning_rate": 2.2545090180360722e-05,
      "loss": 2.1371,
      "step": 50
    },
    {
      "epoch": 0.010354110581901015,
      "eval_loss": 2.0699515342712402,
      "eval_runtime": 22610.0414,
      "eval_samples_per_second": 0.427,
      "eval_steps_per_second": 0.053,
      "step": 50
    },
    {
      "epoch": 0.015531165872851522,
      "grad_norm": 8.709203720092773,
      "learning_rate": 2.1292585170340683e-05,
      "loss": 2.029,
      "step": 75
    },
    {
      "epoch": 0.015531165872851522,
      "eval_loss": 1.951442837715149,
      "eval_runtime": 22577.4979,
      "eval_samples_per_second": 0.428,
      "eval_steps_per_second": 0.054,
      "step": 75
    },
    {
      "epoch": 0.02070822116380203,
      "grad_norm": 9.000727653503418,
      "learning_rate": 2.0040080160320643e-05,
      "loss": 1.9957,
      "step": 100
    },
    {
      "epoch": 0.02070822116380203,
      "eval_loss": 1.8961551189422607,
      "eval_runtime": 22614.8229,
      "eval_samples_per_second": 0.427,
      "eval_steps_per_second": 0.053,
      "step": 100
    },
    {
      "epoch": 0.025885276454752536,
      "grad_norm": 9.183732032775879,
      "learning_rate": 1.87875751503006e-05,
      "loss": 1.9914,
      "step": 125
    },
    {
      "epoch": 0.025885276454752536,
      "eval_loss": 1.862902045249939,
      "eval_runtime": 22598.368,
      "eval_samples_per_second": 0.427,
      "eval_steps_per_second": 0.053,
      "step": 125
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2054266552320000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}