{
  "best_metric": 0.7774524158125915,
  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1990,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7635431918008785,
      "eval_loss": 0.5437253713607788,
      "eval_runtime": 119.9317,
      "eval_samples_per_second": 11.39,
      "eval_steps_per_second": 5.695,
      "step": 199
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.773792093704246,
      "eval_loss": 0.5396685004234314,
      "eval_runtime": 124.413,
      "eval_samples_per_second": 10.98,
      "eval_steps_per_second": 5.49,
      "step": 398
    },
    {
      "epoch": 2.5125628140703515,
      "grad_norm": 592.5914916992188,
      "learning_rate": 7.487437185929649e-06,
      "loss": 0.5014,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7730600292825769,
      "eval_loss": 0.5995632410049438,
      "eval_runtime": 59.0331,
      "eval_samples_per_second": 23.14,
      "eval_steps_per_second": 11.57,
      "step": 597
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7774524158125915,
      "eval_loss": 0.7029575109481812,
      "eval_runtime": 123.6878,
      "eval_samples_per_second": 11.044,
      "eval_steps_per_second": 5.522,
      "step": 796
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7693997071742313,
      "eval_loss": 0.8647988438606262,
      "eval_runtime": 112.0996,
      "eval_samples_per_second": 12.186,
      "eval_steps_per_second": 6.093,
      "step": 995
    },
    {
      "epoch": 5.025125628140704,
      "grad_norm": 2496.794189453125,
      "learning_rate": 4.974874371859297e-06,
      "loss": 0.2005,
      "step": 1000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7642752562225475,
      "eval_loss": 1.0910539627075195,
      "eval_runtime": 111.8459,
      "eval_samples_per_second": 12.213,
      "eval_steps_per_second": 6.107,
      "step": 1194
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7723279648609077,
      "eval_loss": 1.2653732299804688,
      "eval_runtime": 110.9037,
      "eval_samples_per_second": 12.317,
      "eval_steps_per_second": 6.158,
      "step": 1393
    },
    {
      "epoch": 7.5376884422110555,
      "grad_norm": 1611.986083984375,
      "learning_rate": 2.462311557788945e-06,
      "loss": 0.0881,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.773792093704246,
      "eval_loss": 1.5597944259643555,
      "eval_runtime": 115.9058,
      "eval_samples_per_second": 11.785,
      "eval_steps_per_second": 5.893,
      "step": 1592
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7693997071742313,
      "eval_loss": 1.7513818740844727,
      "eval_runtime": 113.5331,
      "eval_samples_per_second": 12.032,
      "eval_steps_per_second": 6.016,
      "step": 1791
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7679355783308931,
      "eval_loss": 1.8216043710708618,
      "eval_runtime": 170.3389,
      "eval_samples_per_second": 8.019,
      "eval_steps_per_second": 4.01,
      "step": 1990
    }
  ],
  "logging_steps": 500,
  "max_steps": 1990,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2.95568855112096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}