{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4275849536616391,
  "eval_steps": 1000,
  "global_step": 2353,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018171906232963838,
      "grad_norm": 7.298370361328125,
      "learning_rate": 0.0,
      "loss": 3.0984,
      "step": 1
    },
    {
      "epoch": 0.1817190623296384,
      "grad_norm": 6.053193092346191,
      "learning_rate": 3.6307468653461755e-06,
      "loss": 2.7134,
      "step": 1000
    },
    {
      "epoch": 0.1817190623296384,
      "eval_cosine_accuracy": 0.9391103386878967,
      "eval_loss": 1.3783869743347168,
      "eval_runtime": 18.26,
      "eval_samples_per_second": 520.755,
      "eval_steps_per_second": 4.107,
      "step": 1000
    },
    {
      "epoch": 0.3634381246592768,
      "grad_norm": 5.73389196395874,
      "learning_rate": 7.265128111938943e-06,
      "loss": 2.1597,
      "step": 2000
    },
    {
      "epoch": 0.3634381246592768,
      "eval_cosine_accuracy": 0.9412136077880859,
      "eval_loss": 1.2863198518753052,
      "eval_runtime": 18.0791,
      "eval_samples_per_second": 525.968,
      "eval_steps_per_second": 4.148,
      "step": 2000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 27515,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}