trainer_state.json

{
  "best_metric": 0.1931125248049425,
  "best_model_checkpoint": "esm2_t6_8M_qlora_binding_sites_2023-09-28_00-05-45/checkpoint-3939",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3939,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0003700096638060586,
      "loss": 0.4987,
      "step": 200
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003695684724487918,
      "loss": 0.3756,
      "step": 400
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00036883393302294926,
      "loss": 0.3422,
      "step": 600
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003678072134814851,
      "loss": 0.3223,
      "step": 800
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003664899463577655,
      "loss": 0.3094,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00036488422616976233,
      "loss": 0.3001,
      "step": 1200
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003629926060896693,
      "loss": 0.2916,
      "step": 1400
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00036081809388423475,
      "loss": 0.2847,
      "step": 1600
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003583641471322691,
      "loss": 0.2787,
      "step": 1800
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00035563466772692797,
      "loss": 0.2725,
      "step": 2000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003526339956715147,
      "loss": 0.2699,
      "step": 2200
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00034936690217866705,
      "loss": 0.2668,
      "step": 2400
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00034583858208389975,
      "loss": 0.2636,
      "step": 2600
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003420546455855667,
      "loss": 0.2604,
      "step": 2800
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00033802110932437625,
      "loss": 0.2577,
      "step": 3000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003337443868166437,
      "loss": 0.2545,
      "step": 3200
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00032923127825649205,
      "loss": 0.2515,
      "step": 3400
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00032448895970321745,
      "loss": 0.2518,
      "step": 3600
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003195503301009428,
      "loss": 0.2465,
      "step": 3800
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8584993872301376,
      "eval_auc": 0.8182032038033911,
      "eval_f1": 0.1931125248049425,
      "eval_loss": 0.4206424355506897,
      "eval_mcc": 0.25789003640920655,
      "eval_precision": 0.11027656492418843,
      "eval_recall": 0.7760683791635847,
      "eval_runtime": 1158.8552,
      "eval_samples_per_second": 110.153,
      "eval_steps_per_second": 1.722,
      "step": 3939
    }
  ],
  "logging_steps": 200,
  "max_steps": 15756,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2.025377780531094e+16,
  "trial_name": null,
  "trial_params": null
}