{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010905601116733554,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010905601116733554,
      "eval_accuracy": 0.5034676821874995,
      "eval_loss": 2.249495029449463,
      "eval_runtime": 250.8322,
      "eval_samples_per_second": 22.182,
      "eval_steps_per_second": 0.088,
      "step": 100
    },
    {
      "epoch": 0.002181120223346711,
      "eval_accuracy": 0.6792460132466641,
      "eval_loss": 1.3580471277236938,
      "eval_runtime": 250.935,
      "eval_samples_per_second": 22.173,
      "eval_steps_per_second": 0.088,
      "step": 200
    },
    {
      "epoch": 0.0032716803350200663,
      "eval_accuracy": 0.7194358306786471,
      "eval_loss": 1.1734950542449951,
      "eval_runtime": 249.8616,
      "eval_samples_per_second": 22.268,
      "eval_steps_per_second": 0.088,
      "step": 300
    },
    {
      "epoch": 0.004362240446693422,
      "eval_accuracy": 0.7406081066868597,
      "eval_loss": 1.0811182260513306,
      "eval_runtime": 250.2334,
      "eval_samples_per_second": 22.235,
      "eval_steps_per_second": 0.088,
      "step": 400
    },
    {
      "epoch": 0.005452800558366777,
      "grad_norm": 1.5124988555908203,
      "learning_rate": 4.990911999069389e-05,
      "loss": 1.8503,
      "step": 500
    },
    {
      "epoch": 0.005452800558366777,
      "eval_accuracy": 0.7539559460484646,
      "eval_loss": 1.0170289278030396,
      "eval_runtime": 250.2283,
      "eval_samples_per_second": 22.236,
      "eval_steps_per_second": 0.088,
      "step": 500
    },
    {
      "epoch": 0.0065433606700401326,
      "eval_accuracy": 0.7639956787495118,
      "eval_loss": 0.9728907346725464,
      "eval_runtime": 250.2409,
      "eval_samples_per_second": 22.235,
      "eval_steps_per_second": 0.088,
      "step": 600
    },
    {
      "epoch": 0.007633920781713488,
      "eval_accuracy": 0.7704801005740811,
      "eval_loss": 0.9435333013534546,
      "eval_runtime": 250.3167,
      "eval_samples_per_second": 22.228,
      "eval_steps_per_second": 0.088,
      "step": 700
    },
    {
      "epoch": 0.008724480893386843,
      "eval_accuracy": 0.7747122964825798,
      "eval_loss": 0.924051821231842,
      "eval_runtime": 250.2963,
      "eval_samples_per_second": 22.23,
      "eval_steps_per_second": 0.088,
      "step": 800
    },
    {
      "epoch": 0.009815041005060199,
      "eval_accuracy": 0.7814711185942613,
      "eval_loss": 0.8970186114311218,
      "eval_runtime": 250.1321,
      "eval_samples_per_second": 22.244,
      "eval_steps_per_second": 0.088,
      "step": 900
    },
    {
      "epoch": 0.010905601116733554,
      "grad_norm": 1.2721333503723145,
      "learning_rate": 4.981823998138778e-05,
      "loss": 0.9214,
      "step": 1000
    },
    {
      "epoch": 0.010905601116733554,
      "eval_accuracy": 0.7872277846758073,
      "eval_loss": 0.8725214004516602,
      "eval_runtime": 249.8439,
      "eval_samples_per_second": 22.27,
      "eval_steps_per_second": 0.088,
      "step": 1000
    },
    {
      "epoch": 0.010905601116733554,
      "step": 1000,
      "total_flos": 1.3069163715939533e+18,
      "train_loss": 1.3858390502929687,
      "train_runtime": 13072.5982,
      "train_samples_per_second": 1346.745,
      "train_steps_per_second": 21.043
    }
  ],
  "logging_steps": 500,
  "max_steps": 275088,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3069163715939533e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}