{
  "best_metric": 0.45830225944519043,
  "best_model_checkpoint": "output_pipe/H3K14ac/origin/checkpoint-800",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 1656,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24154589371980675,
      "grad_norm": 11.506314277648926,
      "learning_rate": 2.9159402241594023e-05,
      "loss": 0.6271,
      "step": 100
    },
    {
      "epoch": 0.4830917874396135,
      "grad_norm": 9.236607551574707,
      "learning_rate": 2.729140722291407e-05,
      "loss": 0.5535,
      "step": 200
    },
    {
      "epoch": 0.4830917874396135,
      "eval_accuracy": 0.7343419062027231,
      "eval_f1": 0.7133185141276428,
      "eval_loss": 0.5373454689979553,
      "eval_matthews_correlation": 0.44477624037072266,
      "eval_precision": 0.7366994754518459,
      "eval_recall": 0.7089420599904968,
      "eval_runtime": 1.4528,
      "eval_samples_per_second": 2274.986,
      "eval_steps_per_second": 35.794,
      "step": 200
    },
    {
      "epoch": 0.7246376811594203,
      "grad_norm": 9.798834800720215,
      "learning_rate": 2.5423412204234122e-05,
      "loss": 0.5338,
      "step": 300
    },
    {
      "epoch": 0.966183574879227,
      "grad_norm": 15.268228530883789,
      "learning_rate": 2.3555417185554173e-05,
      "loss": 0.5348,
      "step": 400
    },
    {
      "epoch": 0.966183574879227,
      "eval_accuracy": 0.7636913767019667,
      "eval_f1": 0.7588137869815574,
      "eval_loss": 0.4984193742275238,
      "eval_matthews_correlation": 0.5184806798756422,
      "eval_precision": 0.7574919840840609,
      "eval_recall": 0.7610005670278928,
      "eval_runtime": 1.4543,
      "eval_samples_per_second": 2272.524,
      "eval_steps_per_second": 35.755,
      "step": 400
    },
    {
      "epoch": 1.2077294685990339,
      "grad_norm": 12.763960838317871,
      "learning_rate": 2.1687422166874224e-05,
      "loss": 0.4238,
      "step": 500
    },
    {
      "epoch": 1.4492753623188406,
      "grad_norm": 22.53868293762207,
      "learning_rate": 1.981942714819427e-05,
      "loss": 0.4121,
      "step": 600
    },
    {
      "epoch": 1.4492753623188406,
      "eval_accuracy": 0.7782148260211801,
      "eval_f1": 0.7714647776060547,
      "eval_loss": 0.4741654098033905,
      "eval_matthews_correlation": 0.5429951223063763,
      "eval_precision": 0.7721092757786799,
      "eval_recall": 0.7708872216913396,
      "eval_runtime": 1.4588,
      "eval_samples_per_second": 2265.607,
      "eval_steps_per_second": 35.646,
      "step": 600
    },
    {
      "epoch": 1.6908212560386473,
      "grad_norm": 24.0648193359375,
      "learning_rate": 1.795143212951432e-05,
      "loss": 0.3915,
      "step": 700
    },
    {
      "epoch": 1.9323671497584543,
      "grad_norm": 16.68227195739746,
      "learning_rate": 1.6083437110834373e-05,
      "loss": 0.3928,
      "step": 800
    },
    {
      "epoch": 1.9323671497584543,
      "eval_accuracy": 0.794553706505295,
      "eval_f1": 0.7860204006226504,
      "eval_loss": 0.45830225944519043,
      "eval_matthews_correlation": 0.5740153805466681,
      "eval_precision": 0.7911242229913217,
      "eval_recall": 0.7829493658399205,
      "eval_runtime": 1.4645,
      "eval_samples_per_second": 2256.693,
      "eval_steps_per_second": 35.506,
      "step": 800
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 11.462382316589355,
      "learning_rate": 1.4215442092154421e-05,
      "loss": 0.2383,
      "step": 900
    },
    {
      "epoch": 2.4154589371980677,
      "grad_norm": 19.372472763061523,
      "learning_rate": 1.234744707347447e-05,
      "loss": 0.1925,
      "step": 1000
    },
    {
      "epoch": 2.4154589371980677,
      "eval_accuracy": 0.8033282904689864,
      "eval_f1": 0.7990361969650139,
      "eval_loss": 0.5815736055374146,
      "eval_matthews_correlation": 0.5986949846890586,
      "eval_precision": 0.7976205363423409,
      "eval_recall": 0.8010844690834253,
      "eval_runtime": 1.4693,
      "eval_samples_per_second": 2249.347,
      "eval_steps_per_second": 35.391,
      "step": 1000
    },
    {
      "epoch": 2.6570048309178746,
      "grad_norm": 17.808015823364258,
      "learning_rate": 1.0479452054794521e-05,
      "loss": 0.1752,
      "step": 1100
    },
    {
      "epoch": 2.898550724637681,
      "grad_norm": 26.556241989135742,
      "learning_rate": 8.61145703611457e-06,
      "loss": 0.1539,
      "step": 1200
    },
    {
      "epoch": 2.898550724637681,
      "eval_accuracy": 0.8087745839636914,
      "eval_f1": 0.8073621388155385,
      "eval_loss": 0.5311077833175659,
      "eval_matthews_correlation": 0.625230657276318,
      "eval_precision": 0.8083090352316981,
      "eval_recall": 0.8169817700155952,
      "eval_runtime": 1.4706,
      "eval_samples_per_second": 2247.352,
      "eval_steps_per_second": 35.359,
      "step": 1200
    },
    {
      "epoch": 3.140096618357488,
      "grad_norm": 34.298770904541016,
      "learning_rate": 6.743462017434621e-06,
      "loss": 0.0919,
      "step": 1300
    },
    {
      "epoch": 3.3816425120772946,
      "grad_norm": 6.062216758728027,
      "learning_rate": 4.87546699875467e-06,
      "loss": 0.0497,
      "step": 1400
    },
    {
      "epoch": 3.3816425120772946,
      "eval_accuracy": 0.8151285930408472,
      "eval_f1": 0.8122103384074125,
      "eval_loss": 1.2530276775360107,
      "eval_matthews_correlation": 0.6272121453815194,
      "eval_precision": 0.810373052699281,
      "eval_recall": 0.8168727696338114,
      "eval_runtime": 1.4716,
      "eval_samples_per_second": 2245.812,
      "eval_steps_per_second": 35.335,
      "step": 1400
    },
    {
      "epoch": 3.6231884057971016,
      "grad_norm": 35.668251037597656,
      "learning_rate": 3.0261519302615196e-06,
      "loss": 0.044,
      "step": 1500
    },
    {
      "epoch": 3.864734299516908,
      "grad_norm": 30.958539962768555,
      "learning_rate": 1.1581569115815693e-06,
      "loss": 0.0324,
      "step": 1600
    },
    {
      "epoch": 3.864734299516908,
      "eval_accuracy": 0.8190620272314675,
      "eval_f1": 0.8138504481777521,
      "eval_loss": 1.126000165939331,
      "eval_matthews_correlation": 0.6277065380598288,
      "eval_precision": 0.8140494964254426,
      "eval_recall": 0.8136571642430555,
      "eval_runtime": 1.4724,
      "eval_samples_per_second": 2244.565,
      "eval_steps_per_second": 35.315,
      "step": 1600
    },
    {
      "epoch": 4.0,
      "step": 1656,
      "total_flos": 8336831279874048.0,
      "train_loss": 0.2935135773414575,
      "train_runtime": 166.6842,
      "train_samples_per_second": 634.445,
      "train_steps_per_second": 9.935
    }
  ],
  "logging_steps": 100,
  "max_steps": 1656,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 8336831279874048.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}