{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9727463312368974,
  "eval_steps": 500,
  "global_step": 177,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 2.3957157024988684,
      "learning_rate": 5e-06,
      "loss": 0.9066,
      "step": 10
    },
    {
      "epoch": 0.33542976939203356,
      "grad_norm": 0.9746040571492541,
      "learning_rate": 5e-06,
      "loss": 0.787,
      "step": 20
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 0.8344916856818549,
      "learning_rate": 5e-06,
      "loss": 0.7455,
      "step": 30
    },
    {
      "epoch": 0.6708595387840671,
      "grad_norm": 0.6630661792183175,
      "learning_rate": 5e-06,
      "loss": 0.7233,
      "step": 40
    },
    {
      "epoch": 0.8385744234800838,
      "grad_norm": 0.5831963334305033,
      "learning_rate": 5e-06,
      "loss": 0.7147,
      "step": 50
    },
    {
      "epoch": 0.989517819706499,
      "eval_loss": 0.6969855427742004,
      "eval_runtime": 65.5762,
      "eval_samples_per_second": 24.506,
      "eval_steps_per_second": 0.396,
      "step": 59
    },
    {
      "epoch": 1.0083857442348008,
      "grad_norm": 1.2448623688206673,
      "learning_rate": 5e-06,
      "loss": 0.7324,
      "step": 60
    },
    {
      "epoch": 1.1761006289308176,
      "grad_norm": 0.664663255277509,
      "learning_rate": 5e-06,
      "loss": 0.6726,
      "step": 70
    },
    {
      "epoch": 1.3438155136268344,
      "grad_norm": 0.6046916264157929,
      "learning_rate": 5e-06,
      "loss": 0.6595,
      "step": 80
    },
    {
      "epoch": 1.5115303983228512,
      "grad_norm": 0.5743588500421465,
      "learning_rate": 5e-06,
      "loss": 0.6558,
      "step": 90
    },
    {
      "epoch": 1.6792452830188678,
      "grad_norm": 0.43743628219913383,
      "learning_rate": 5e-06,
      "loss": 0.6525,
      "step": 100
    },
    {
      "epoch": 1.8469601677148848,
      "grad_norm": 0.46309281832033367,
      "learning_rate": 5e-06,
      "loss": 0.6543,
      "step": 110
    },
    {
      "epoch": 1.9979035639412999,
      "eval_loss": 0.6759442090988159,
      "eval_runtime": 65.7618,
      "eval_samples_per_second": 24.437,
      "eval_steps_per_second": 0.395,
      "step": 119
    },
    {
      "epoch": 2.0167714884696015,
      "grad_norm": 1.5249649463375206,
      "learning_rate": 5e-06,
      "loss": 0.6821,
      "step": 120
    },
    {
      "epoch": 2.1844863731656186,
      "grad_norm": 0.7389955715272274,
      "learning_rate": 5e-06,
      "loss": 0.6222,
      "step": 130
    },
    {
      "epoch": 2.352201257861635,
      "grad_norm": 0.6349772661501074,
      "learning_rate": 5e-06,
      "loss": 0.6206,
      "step": 140
    },
    {
      "epoch": 2.519916142557652,
      "grad_norm": 0.545238991522723,
      "learning_rate": 5e-06,
      "loss": 0.6165,
      "step": 150
    },
    {
      "epoch": 2.6876310272536688,
      "grad_norm": 0.6862197330555269,
      "learning_rate": 5e-06,
      "loss": 0.6165,
      "step": 160
    },
    {
      "epoch": 2.8553459119496853,
      "grad_norm": 0.4711708638765378,
      "learning_rate": 5e-06,
      "loss": 0.6175,
      "step": 170
    },
    {
      "epoch": 2.9727463312368974,
      "eval_loss": 0.6712015867233276,
      "eval_runtime": 64.8268,
      "eval_samples_per_second": 24.789,
      "eval_steps_per_second": 0.401,
      "step": 177
    },
    {
      "epoch": 2.9727463312368974,
      "step": 177,
      "total_flos": 296272212787200.0,
      "train_loss": 0.6840900243338892,
      "train_runtime": 10713.9597,
      "train_samples_per_second": 8.545,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 177,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 296272212787200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}