{
  "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": 3.650646209716797,
      "learning_rate": 3e-06,
      "loss": 2.4534,
      "step": 1
    },
    {
      "epoch": 0.008782484213484626,
      "grad_norm": 7.008567810058594,
      "learning_rate": 2.9736788948121867e-06,
      "loss": 0.9508,
      "step": 1000
    },
    {
      "epoch": 0.008782484213484626,
      "eval_accuracy": 0.8620952367782593,
      "eval_loss": 0.6480623483657837,
      "eval_runtime": 91.7053,
      "eval_samples_per_second": 100.343,
      "eval_steps_per_second": 12.551,
      "step": 1000
    },
    {
      "epoch": 0.017564968426969252,
      "grad_norm": 7.082250595092773,
      "learning_rate": 2.9473314421717326e-06,
      "loss": 0.5848,
      "step": 2000
    },
    {
      "epoch": 0.017564968426969252,
      "eval_accuracy": 0.8683981895446777,
      "eval_loss": 0.5488540530204773,
      "eval_runtime": 88.6005,
      "eval_samples_per_second": 103.86,
      "eval_steps_per_second": 12.991,
      "step": 2000
    },
    {
      "epoch": 0.026347452640453878,
      "grad_norm": 9.752965927124023,
      "learning_rate": 2.920983989531279e-06,
      "loss": 0.538,
      "step": 3000
    },
    {
      "epoch": 0.026347452640453878,
      "eval_accuracy": 0.8763312697410583,
      "eval_loss": 0.5032069683074951,
      "eval_runtime": 91.911,
      "eval_samples_per_second": 100.119,
      "eval_steps_per_second": 12.523,
      "step": 3000
    },
    {
      "epoch": 0.035129936853938504,
      "grad_norm": 18.048477172851562,
      "learning_rate": 2.8946365368908247e-06,
      "loss": 0.4917,
      "step": 4000
    },
    {
      "epoch": 0.035129936853938504,
      "eval_accuracy": 0.8798087239265442,
      "eval_loss": 0.4753971993923187,
      "eval_runtime": 87.1557,
      "eval_samples_per_second": 105.581,
      "eval_steps_per_second": 13.206,
      "step": 4000
    },
    {
      "epoch": 0.04391242106742313,
      "grad_norm": 3.9426069259643555,
      "learning_rate": 2.868289084250371e-06,
      "loss": 0.4623,
      "step": 5000
    },
    {
      "epoch": 0.04391242106742313,
      "eval_accuracy": 0.8830689191818237,
      "eval_loss": 0.4554503560066223,
      "eval_runtime": 90.2062,
      "eval_samples_per_second": 102.011,
      "eval_steps_per_second": 12.76,
      "step": 5000
    },
    {
      "epoch": 0.052694905280907756,
      "grad_norm": 7.809971809387207,
      "learning_rate": 2.8419416316099173e-06,
      "loss": 0.4674,
      "step": 6000
    },
    {
      "epoch": 0.052694905280907756,
      "eval_accuracy": 0.885568380355835,
      "eval_loss": 0.439510315656662,
      "eval_runtime": 89.324,
      "eval_samples_per_second": 103.018,
      "eval_steps_per_second": 12.886,
      "step": 6000
    },
    {
      "epoch": 0.06147738949439238,
      "grad_norm": 11.946690559387207,
      "learning_rate": 2.8155941789694636e-06,
      "loss": 0.435,
      "step": 7000
    },
    {
      "epoch": 0.06147738949439238,
      "eval_accuracy": 0.8866550922393799,
      "eval_loss": 0.4272012412548065,
      "eval_runtime": 88.643,
      "eval_samples_per_second": 103.81,
      "eval_steps_per_second": 12.985,
      "step": 7000
    },
    {
      "epoch": 0.07025987370787701,
      "grad_norm": 8.120018005371094,
      "learning_rate": 2.7892467263290094e-06,
      "loss": 0.4202,
      "step": 8000
    },
    {
      "epoch": 0.07025987370787701,
      "eval_accuracy": 0.8886111974716187,
      "eval_loss": 0.41821107268333435,
      "eval_runtime": 86.7283,
      "eval_samples_per_second": 106.101,
      "eval_steps_per_second": 13.271,
      "step": 8000
    },
    {
      "epoch": 0.07904235792136163,
      "grad_norm": 9.031862258911133,
      "learning_rate": 2.7628992736885557e-06,
      "loss": 0.4149,
      "step": 9000
    },
    {
      "epoch": 0.07904235792136163,
      "eval_accuracy": 0.8927407264709473,
      "eval_loss": 0.4074467420578003,
      "eval_runtime": 89.6748,
      "eval_samples_per_second": 102.615,
      "eval_steps_per_second": 12.835,
      "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
}