{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0265486725663717,
  "eval_steps": 6,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.035398230088495575,
      "eval_loss": 1.240618109703064,
      "eval_runtime": 2.7363,
      "eval_samples_per_second": 69.437,
      "eval_steps_per_second": 8.771,
      "step": 1
    },
    {
      "epoch": 0.21238938053097345,
      "eval_loss": 0.9170649647712708,
      "eval_runtime": 2.7141,
      "eval_samples_per_second": 70.004,
      "eval_steps_per_second": 8.843,
      "step": 6
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 1.608567714691162,
      "learning_rate": 7.985792958513931e-05,
      "loss": 0.9919,
      "step": 10
    },
    {
      "epoch": 0.4247787610619469,
      "eval_loss": 0.4827438294887543,
      "eval_runtime": 2.7038,
      "eval_samples_per_second": 70.272,
      "eval_steps_per_second": 8.876,
      "step": 12
    },
    {
      "epoch": 0.6371681415929203,
      "eval_loss": 0.24917787313461304,
      "eval_runtime": 2.7038,
      "eval_samples_per_second": 70.271,
      "eval_steps_per_second": 8.876,
      "step": 18
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.9552421569824219,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3935,
      "step": 20
    },
    {
      "epoch": 0.8495575221238938,
      "eval_loss": 0.17106853425502777,
      "eval_runtime": 2.7134,
      "eval_samples_per_second": 70.023,
      "eval_steps_per_second": 8.845,
      "step": 24
    }
  ],
  "logging_steps": 10,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1143271002669056e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}