{
  "best_global_step": 50,
  "best_metric": 0.4943101406097412,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.19404008984565735,
      "learning_rate": 3.6e-05,
      "loss": 1.1482,
      "step": 10
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.2238703817129135,
      "learning_rate": 7.6e-05,
      "loss": 1.0168,
      "step": 20
    },
    {
      "epoch": 1.372093023255814,
      "grad_norm": 0.4696136713027954,
      "learning_rate": 0.000116,
      "loss": 0.8916,
      "step": 30
    },
    {
      "epoch": 1.8372093023255816,
      "grad_norm": 0.36445125937461853,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.8051,
      "step": 40
    },
    {
      "epoch": 2.2790697674418605,
      "grad_norm": 0.3186148405075073,
      "learning_rate": 0.000196,
      "loss": 0.5696,
      "step": 50
    },
    {
      "epoch": 2.2790697674418605,
      "eval_loss": 0.4943101406097412,
      "eval_runtime": 2.152,
      "eval_samples_per_second": 9.294,
      "eval_steps_per_second": 1.394,
      "step": 50
    },
    {
      "epoch": 2.744186046511628,
      "grad_norm": 0.44536513090133667,
      "learning_rate": 8.75e-05,
      "loss": 0.4707,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2032140313165824.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}