{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08343360002810395,
  "eval_steps": 1000,
  "global_step": 9500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.782484213484626e-06,
      "grad_norm": 3.6796653270721436,
      "learning_rate": 3e-06,
      "loss": 2.5344,
      "step": 1
    },
    {
      "epoch": 0.008782484213484626,
      "grad_norm": 8.691473007202148,
      "learning_rate": 2.9736788948121867e-06,
      "loss": 1.0666,
      "step": 1000
    },
    {
      "epoch": 0.008782484213484626,
      "eval_accuracy": 0.8495979309082031,
      "eval_loss": 0.7292845845222473,
      "eval_runtime": 85.0016,
      "eval_samples_per_second": 108.257,
      "eval_steps_per_second": 13.541,
      "step": 1000
    },
    {
      "epoch": 0.017564968426969252,
      "grad_norm": 6.969796657562256,
      "learning_rate": 2.9473314421717326e-06,
      "loss": 0.6516,
      "step": 2000
    },
    {
      "epoch": 0.017564968426969252,
      "eval_accuracy": 0.8538361191749573,
      "eval_loss": 0.6177436113357544,
      "eval_runtime": 82.38,
      "eval_samples_per_second": 111.702,
      "eval_steps_per_second": 13.972,
      "step": 2000
    },
    {
      "epoch": 0.026347452640453878,
      "grad_norm": 19.85172462463379,
      "learning_rate": 2.920983989531279e-06,
      "loss": 0.6072,
      "step": 3000
    },
    {
      "epoch": 0.026347452640453878,
      "eval_accuracy": 0.8620952367782593,
      "eval_loss": 0.5767402648925781,
      "eval_runtime": 84.8181,
      "eval_samples_per_second": 108.491,
      "eval_steps_per_second": 13.57,
      "step": 3000
    },
    {
      "epoch": 0.035129936853938504,
      "grad_norm": 10.813929557800293,
      "learning_rate": 2.8946365368908247e-06,
      "loss": 0.5674,
      "step": 4000
    },
    {
      "epoch": 0.035129936853938504,
      "eval_accuracy": 0.8662247657775879,
      "eval_loss": 0.5505204200744629,
      "eval_runtime": 79.8645,
      "eval_samples_per_second": 115.22,
      "eval_steps_per_second": 14.412,
      "step": 4000
    },
    {
      "epoch": 0.04391242106742313,
      "grad_norm": 7.621878623962402,
      "learning_rate": 2.868289084250371e-06,
      "loss": 0.5299,
      "step": 5000
    },
    {
      "epoch": 0.04391242106742313,
      "eval_accuracy": 0.8677461743354797,
      "eval_loss": 0.5321353077888489,
      "eval_runtime": 93.9377,
      "eval_samples_per_second": 97.959,
      "eval_steps_per_second": 12.253,
      "step": 5000
    },
    {
      "epoch": 0.052694905280907756,
      "grad_norm": 7.295602321624756,
      "learning_rate": 2.8419416316099173e-06,
      "loss": 0.5388,
      "step": 6000
    },
    {
      "epoch": 0.052694905280907756,
      "eval_accuracy": 0.8685068488121033,
      "eval_loss": 0.5172874331474304,
      "eval_runtime": 77.0511,
      "eval_samples_per_second": 119.427,
      "eval_steps_per_second": 14.938,
      "step": 6000
    },
    {
      "epoch": 0.06147738949439238,
      "grad_norm": 21.50514030456543,
      "learning_rate": 2.8155941789694636e-06,
      "loss": 0.5005,
      "step": 7000
    },
    {
      "epoch": 0.06147738949439238,
      "eval_accuracy": 0.871549665927887,
      "eval_loss": 0.49886903166770935,
      "eval_runtime": 80.8123,
      "eval_samples_per_second": 113.869,
      "eval_steps_per_second": 14.243,
      "step": 7000
    },
    {
      "epoch": 0.07025987370787701,
      "grad_norm": 12.609434127807617,
      "learning_rate": 2.7892467263290094e-06,
      "loss": 0.4776,
      "step": 8000
    },
    {
      "epoch": 0.07025987370787701,
      "eval_accuracy": 0.874266505241394,
      "eval_loss": 0.48554736375808716,
      "eval_runtime": 79.5335,
      "eval_samples_per_second": 115.7,
      "eval_steps_per_second": 14.472,
      "step": 8000
    },
    {
      "epoch": 0.07904235792136163,
      "grad_norm": 12.605308532714844,
      "learning_rate": 2.7628992736885557e-06,
      "loss": 0.4744,
      "step": 9000
    },
    {
      "epoch": 0.07904235792136163,
      "eval_accuracy": 0.87557053565979,
      "eval_loss": 0.4739709198474884,
      "eval_runtime": 83.1212,
      "eval_samples_per_second": 110.706,
      "eval_steps_per_second": 13.847,
      "step": 9000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 113863,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}