{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2226,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5854838709677419,
      "eval_loss": 0.20778915286064148,
      "eval_runtime": 1.5277,
      "eval_samples_per_second": 2029.22,
      "eval_steps_per_second": 42.548,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.6138257384300232,
      "learning_rate": 1.550763701707098e-05,
      "loss": 0.3302,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8238709677419355,
      "eval_loss": 0.10201918333768845,
      "eval_runtime": 1.6113,
      "eval_samples_per_second": 1923.963,
      "eval_steps_per_second": 40.341,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8767741935483871,
      "eval_loss": 0.06950849294662476,
      "eval_runtime": 1.5225,
      "eval_samples_per_second": 2036.166,
      "eval_steps_per_second": 42.694,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.5043034553527832,
      "learning_rate": 1.101527403414196e-05,
      "loss": 0.1186,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8948387096774194,
      "eval_loss": 0.05494268983602524,
      "eval_runtime": 1.6072,
      "eval_samples_per_second": 1928.783,
      "eval_steps_per_second": 40.442,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.3357006311416626,
      "learning_rate": 6.522911051212939e-06,
      "loss": 0.0778,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9009677419354839,
      "eval_loss": 0.0461166575551033,
      "eval_runtime": 1.521,
      "eval_samples_per_second": 2038.178,
      "eval_steps_per_second": 42.736,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9070967741935484,
      "eval_loss": 0.042120084166526794,
      "eval_runtime": 1.5305,
      "eval_samples_per_second": 2025.457,
      "eval_steps_per_second": 42.469,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.29327207803726196,
      "learning_rate": 2.0305480682839176e-06,
      "loss": 0.0638,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2226,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 520991326672152.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.7135847914278676,
    "num_train_epochs": 7,
    "temperature": 9
  }
}