{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 11.864406779661017,
  "eval_steps": 500,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.237288135593221,
      "grad_norm": 0.3329339027404785,
      "learning_rate": 1.7937853107344636e-05,
      "loss": 0.1429,
      "step": 500
    },
    {
      "epoch": 4.237288135593221,
      "eval_loss": 0.01928097940981388,
      "eval_runtime": 581.4805,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.052,
      "step": 500
    },
    {
      "epoch": 8.474576271186441,
      "grad_norm": 0.2980363368988037,
      "learning_rate": 1.0875706214689265e-05,
      "loss": 0.0145,
      "step": 1000
    },
    {
      "epoch": 8.474576271186441,
      "eval_loss": 0.008630430325865746,
      "eval_runtime": 580.8156,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.052,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1770,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2922151104977306e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}