{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9777777777777777,
  "eval_steps": 500,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 8.899718284606934,
      "learning_rate": 1.9941379571543597e-05,
      "loss": 1.6146,
      "step": 5
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 16.135953903198242,
      "learning_rate": 1.796093065705644e-05,
      "loss": 1.0589,
      "step": 10
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.037100315093994,
      "learning_rate": 1.3701381553399147e-05,
      "loss": 0.9919,
      "step": 15
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 2.2769477367401123,
      "learning_rate": 8.382180034472353e-06,
      "loss": 0.9477,
      "step": 20
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.6512153148651123,
      "learning_rate": 3.5261371521817247e-06,
      "loss": 0.9219,
      "step": 25
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.4710832834243774,
      "learning_rate": 5.234682881719766e-07,
      "loss": 0.9062,
      "step": 30
    },
    {
      "epoch": 0.9777777777777777,
      "step": 33,
      "total_flos": 8.982325273768755e+16,
      "train_loss": 1.056926799542976,
      "train_runtime": 683.8851,
      "train_samples_per_second": 3.136,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 5,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8.982325273768755e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}