{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.888888888888889,
  "eval_steps": 500,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.2242259383201599,
      "learning_rate": 9.936341773606723e-05,
      "loss": 0.1132,
      "step": 10
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3236077129840851,
      "learning_rate": 8.849169917149531e-05,
      "loss": 0.0618,
      "step": 20
    },
    {
      "epoch": 1.3111111111111111,
      "grad_norm": 0.23153884708881378,
      "learning_rate": 6.696194330590151e-05,
      "loss": 0.0419,
      "step": 30
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.32238835096359253,
      "learning_rate": 4.0735563795644294e-05,
      "loss": 0.0431,
      "step": 40
    },
    {
      "epoch": 2.1777777777777776,
      "grad_norm": 0.13999998569488525,
      "learning_rate": 1.7074431046748075e-05,
      "loss": 0.0336,
      "step": 50
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.13561949133872986,
      "learning_rate": 2.530119576580936e-06,
      "loss": 0.033,
      "step": 60
    },
    {
      "epoch": 2.888888888888889,
      "step": 66,
      "total_flos": 1384538209542144.0,
      "train_loss": 0.05243030935525894,
      "train_runtime": 827.7821,
      "train_samples_per_second": 0.326,
      "train_steps_per_second": 0.08
    }
  ],
  "logging_steps": 10,
  "max_steps": 66,
  "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": 1384538209542144.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}