{
  "best_metric": 0.7777777777777778,
  "best_model_checkpoint": "/home/ubuntu/.cache/huggingface/checkpoints/final-nolowercase/allenai/scibert_scivocab_cased-zo_up/checkpoint-952",
  "epoch": 14.0,
  "eval_steps": 500,
  "global_step": 952,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 9.758819580078125,
      "learning_rate": 1.9e-05,
      "loss": 2.1465,
      "step": 68
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6060606060606061,
      "eval_f1": 0.5926804543443077,
      "eval_loss": 1.737682580947876,
      "eval_precision": 0.6542157960050116,
      "eval_recall": 0.6060606060606061,
      "eval_runtime": 5.5219,
      "eval_samples_per_second": 35.858,
      "eval_steps_per_second": 3.079,
      "step": 68
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.286689758300781,
      "learning_rate": 1.8e-05,
      "loss": 1.3152,
      "step": 136
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6919191919191919,
      "eval_f1": 0.6839311008227865,
      "eval_loss": 1.176934838294983,
      "eval_precision": 0.6962589879256545,
      "eval_recall": 0.6919191919191919,
      "eval_runtime": 5.5816,
      "eval_samples_per_second": 35.474,
      "eval_steps_per_second": 3.046,
      "step": 136
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.378315925598145,
      "learning_rate": 1.7e-05,
      "loss": 0.7672,
      "step": 204
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7222222222222222,
      "eval_f1": 0.7126444337555448,
      "eval_loss": 0.9430862069129944,
      "eval_precision": 0.7326162263662264,
      "eval_recall": 0.7222222222222222,
      "eval_runtime": 5.5762,
      "eval_samples_per_second": 35.508,
      "eval_steps_per_second": 3.049,
      "step": 204
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.346803665161133,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.428,
      "step": 272
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7424242424242424,
      "eval_f1": 0.7374161797373577,
      "eval_loss": 0.8948661684989929,
      "eval_precision": 0.7697136967970301,
      "eval_recall": 0.7424242424242424,
      "eval_runtime": 5.5678,
      "eval_samples_per_second": 35.561,
      "eval_steps_per_second": 3.053,
      "step": 272
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.8745429515838623,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.2365,
      "step": 340
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7474747474747475,
      "eval_f1": 0.7421610878166268,
      "eval_loss": 0.9098976850509644,
      "eval_precision": 0.7533454200120868,
      "eval_recall": 0.7474747474747475,
      "eval_runtime": 5.5605,
      "eval_samples_per_second": 35.608,
      "eval_steps_per_second": 3.057,
      "step": 340
    },
    {
      "epoch": 6.0,
      "grad_norm": 40.36902618408203,
      "learning_rate": 1.4e-05,
      "loss": 0.1471,
      "step": 408
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7575757575757576,
      "eval_f1": 0.7509465650386367,
      "eval_loss": 0.9332886338233948,
      "eval_precision": 0.7571138737805404,
      "eval_recall": 0.7575757575757576,
      "eval_runtime": 5.5624,
      "eval_samples_per_second": 35.596,
      "eval_steps_per_second": 3.056,
      "step": 408
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.5145724415779114,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0813,
      "step": 476
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7626262626262627,
      "eval_f1": 0.7568973419007069,
      "eval_loss": 1.031730055809021,
      "eval_precision": 0.7752156022989356,
      "eval_recall": 0.7626262626262627,
      "eval_runtime": 5.5746,
      "eval_samples_per_second": 35.518,
      "eval_steps_per_second": 3.05,
      "step": 476
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.22983932495117188,
      "learning_rate": 1.2e-05,
      "loss": 0.0489,
      "step": 544
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7727272727272727,
      "eval_f1": 0.7666605746845349,
      "eval_loss": 1.0123027563095093,
      "eval_precision": 0.7856826316385139,
      "eval_recall": 0.7727272727272727,
      "eval_runtime": 5.5743,
      "eval_samples_per_second": 35.52,
      "eval_steps_per_second": 3.05,
      "step": 544
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.1842876672744751,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.032,
      "step": 612
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7727272727272727,
      "eval_f1": 0.7671998708627763,
      "eval_loss": 1.100764513015747,
      "eval_precision": 0.7916376062209396,
      "eval_recall": 0.7727272727272727,
      "eval_runtime": 5.5601,
      "eval_samples_per_second": 35.611,
      "eval_steps_per_second": 3.057,
      "step": 612
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4087672233581543,
      "learning_rate": 1e-05,
      "loss": 0.0213,
      "step": 680
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7727272727272727,
      "eval_f1": 0.7671998708627763,
      "eval_loss": 1.0900105237960815,
      "eval_precision": 0.7916376062209396,
      "eval_recall": 0.7727272727272727,
      "eval_runtime": 5.5654,
      "eval_samples_per_second": 35.577,
      "eval_steps_per_second": 3.055,
      "step": 680
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.11046537756919861,
      "learning_rate": 9e-06,
      "loss": 0.0175,
      "step": 748
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.7676767676767676,
      "eval_f1": 0.7623911252744204,
      "eval_loss": 1.0985959768295288,
      "eval_precision": 0.7916245791245792,
      "eval_recall": 0.7676767676767676,
      "eval_runtime": 5.5637,
      "eval_samples_per_second": 35.588,
      "eval_steps_per_second": 3.056,
      "step": 748
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.5795270204544067,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0105,
      "step": 816
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.7575757575757576,
      "eval_f1": 0.753315419105508,
      "eval_loss": 1.2046688795089722,
      "eval_precision": 0.7807447182447182,
      "eval_recall": 0.7575757575757576,
      "eval_runtime": 5.5698,
      "eval_samples_per_second": 35.549,
      "eval_steps_per_second": 3.052,
      "step": 816
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.07767060399055481,
      "learning_rate": 7e-06,
      "loss": 0.0099,
      "step": 884
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.7727272727272727,
      "eval_f1": 0.7671686533256058,
      "eval_loss": 1.1359951496124268,
      "eval_precision": 0.7919163438900281,
      "eval_recall": 0.7727272727272727,
      "eval_runtime": 5.5591,
      "eval_samples_per_second": 35.617,
      "eval_steps_per_second": 3.058,
      "step": 884
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.0792476162314415,
      "learning_rate": 6e-06,
      "loss": 0.0072,
      "step": 952
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.7777777777777778,
      "eval_f1": 0.7736904539650535,
      "eval_loss": 1.1267083883285522,
      "eval_precision": 0.797784549758234,
      "eval_recall": 0.7777777777777778,
      "eval_runtime": 5.5659,
      "eval_samples_per_second": 35.574,
      "eval_steps_per_second": 3.054,
      "step": 952
    }
  ],
  "logging_steps": 500,
  "max_steps": 1360,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2984107995832320.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}