{
  "best_global_step": 32,
  "best_metric": 0.8888888888888888,
  "best_model_checkpoint": "symbols_clf/checkpoint-32",
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.05555555555555555,
      "eval_loss": 3.1174912452697754,
      "eval_runtime": 0.093,
      "eval_samples_per_second": 193.626,
      "eval_steps_per_second": 10.757,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.16666666666666666,
      "eval_loss": 2.874302387237549,
      "eval_runtime": 0.0617,
      "eval_samples_per_second": 291.64,
      "eval_steps_per_second": 16.202,
      "step": 8
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3333333333333333,
      "eval_loss": 2.5718352794647217,
      "eval_runtime": 0.0537,
      "eval_samples_per_second": 335.145,
      "eval_steps_per_second": 18.619,
      "step": 12
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 2.2845373153686523,
      "eval_runtime": 0.0546,
      "eval_samples_per_second": 329.739,
      "eval_steps_per_second": 18.319,
      "step": 16
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 2.1046838760375977,
      "eval_runtime": 0.0585,
      "eval_samples_per_second": 307.55,
      "eval_steps_per_second": 17.086,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 1.9366213083267212,
      "eval_runtime": 0.0597,
      "eval_samples_per_second": 301.535,
      "eval_steps_per_second": 16.752,
      "step": 24
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 1.7910093069076538,
      "eval_runtime": 0.075,
      "eval_samples_per_second": 239.946,
      "eval_steps_per_second": 13.33,
      "step": 28
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.6815359592437744,
      "eval_runtime": 0.0771,
      "eval_samples_per_second": 233.408,
      "eval_steps_per_second": 12.967,
      "step": 32
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.5946409702301025,
      "eval_runtime": 0.0592,
      "eval_samples_per_second": 303.938,
      "eval_steps_per_second": 16.885,
      "step": 36
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.505096197128296,
      "eval_runtime": 0.0586,
      "eval_samples_per_second": 307.08,
      "eval_steps_per_second": 17.06,
      "step": 40
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.3820862770080566,
      "eval_runtime": 0.0541,
      "eval_samples_per_second": 332.597,
      "eval_steps_per_second": 18.478,
      "step": 44
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.2910130023956299,
      "eval_runtime": 0.0536,
      "eval_samples_per_second": 335.992,
      "eval_steps_per_second": 18.666,
      "step": 48
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.26617431640625,
      "eval_runtime": 0.062,
      "eval_samples_per_second": 290.286,
      "eval_steps_per_second": 16.127,
      "step": 52
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.2407567501068115,
      "eval_runtime": 0.0543,
      "eval_samples_per_second": 331.4,
      "eval_steps_per_second": 18.411,
      "step": 56
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.1884442567825317,
      "eval_runtime": 0.0521,
      "eval_samples_per_second": 345.745,
      "eval_steps_per_second": 19.208,
      "step": 60
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.1120694875717163,
      "eval_runtime": 0.0529,
      "eval_samples_per_second": 340.484,
      "eval_steps_per_second": 18.916,
      "step": 64
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.114011287689209,
      "eval_runtime": 0.0536,
      "eval_samples_per_second": 335.529,
      "eval_steps_per_second": 18.641,
      "step": 68
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.0817580223083496,
      "eval_runtime": 0.0535,
      "eval_samples_per_second": 336.377,
      "eval_steps_per_second": 18.688,
      "step": 72
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.0812649726867676,
      "eval_runtime": 0.0575,
      "eval_samples_per_second": 313.265,
      "eval_steps_per_second": 17.404,
      "step": 76
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 1.0582048892974854,
      "eval_runtime": 0.0524,
      "eval_samples_per_second": 343.428,
      "eval_steps_per_second": 19.079,
      "step": 80
    },
    {
      "epoch": 20.0,
      "step": 80,
      "total_flos": 2730469925191680.0,
      "train_loss": 1.9437339782714844,
      "train_runtime": 10.2462,
      "train_samples_per_second": 191.29,
      "train_steps_per_second": 7.808
    }
  ],
  "logging_steps": 500,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 2730469925191680.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}