{
  "best_metric": 0.8709677419354839,
  "best_model_checkpoint": "ESMC_plus-finetuned-TP53_201AA/checkpoint-800",
  "epoch": 36.36363636363637,
  "eval_steps": 50,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 3.7824575901031494,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 0.6625,
      "step": 50
    },
    {
      "epoch": 2.2727272727272725,
      "eval_f1_score": 0.7755102040816326,
      "eval_loss": 0.5577281713485718,
      "eval_precision": 0.6855670103092784,
      "eval_recall": 0.8926174496644296,
      "eval_roc_auc": 0.7809697045725397,
      "eval_runtime": 0.5094,
      "eval_samples_per_second": 693.021,
      "eval_steps_per_second": 5.89,
      "step": 50
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 10.261860847473145,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.4772,
      "step": 100
    },
    {
      "epoch": 4.545454545454545,
      "eval_f1_score": 0.7908496732026143,
      "eval_loss": 0.5206712484359741,
      "eval_precision": 0.7707006369426752,
      "eval_recall": 0.8120805369127517,
      "eval_roc_auc": 0.80794078906103,
      "eval_runtime": 0.5068,
      "eval_samples_per_second": 696.586,
      "eval_steps_per_second": 5.92,
      "step": 100
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 11.708925247192383,
      "learning_rate": 5.1e-05,
      "loss": 0.4047,
      "step": 150
    },
    {
      "epoch": 6.818181818181818,
      "eval_f1_score": 0.7753623188405797,
      "eval_loss": 0.49258285760879517,
      "eval_precision": 0.84251968503937,
      "eval_recall": 0.7181208053691275,
      "eval_roc_auc": 0.8690334316000753,
      "eval_runtime": 0.5185,
      "eval_samples_per_second": 680.81,
      "eval_steps_per_second": 5.786,
      "step": 150
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 14.289894104003906,
      "learning_rate": 4.8e-05,
      "loss": 0.3611,
      "step": 200
    },
    {
      "epoch": 9.090909090909092,
      "eval_f1_score": 0.7753623188405797,
      "eval_loss": 0.46306541562080383,
      "eval_precision": 0.84251968503937,
      "eval_recall": 0.7181208053691275,
      "eval_roc_auc": 0.8886658721696042,
      "eval_runtime": 0.487,
      "eval_samples_per_second": 724.818,
      "eval_steps_per_second": 6.16,
      "step": 200
    },
    {
      "epoch": 11.363636363636363,
      "grad_norm": 2.303349494934082,
      "learning_rate": 4.5e-05,
      "loss": 0.3402,
      "step": 250
    },
    {
      "epoch": 11.363636363636363,
      "eval_f1_score": 0.8417508417508418,
      "eval_loss": 0.39569616317749023,
      "eval_precision": 0.8445945945945946,
      "eval_recall": 0.8389261744966443,
      "eval_roc_auc": 0.8988270714420122,
      "eval_runtime": 0.4881,
      "eval_samples_per_second": 723.205,
      "eval_steps_per_second": 6.146,
      "step": 250
    },
    {
      "epoch": 13.636363636363637,
      "grad_norm": 4.852221488952637,
      "learning_rate": 4.2e-05,
      "loss": 0.3342,
      "step": 300
    },
    {
      "epoch": 13.636363636363637,
      "eval_f1_score": 0.8617363344051447,
      "eval_loss": 0.42518067359924316,
      "eval_precision": 0.8271604938271605,
      "eval_recall": 0.8993288590604027,
      "eval_roc_auc": 0.8945618766856928,
      "eval_runtime": 0.4865,
      "eval_samples_per_second": 725.541,
      "eval_steps_per_second": 6.166,
      "step": 300
    },
    {
      "epoch": 15.909090909090908,
      "grad_norm": 5.0347747802734375,
      "learning_rate": 3.9e-05,
      "loss": 0.2885,
      "step": 350
    },
    {
      "epoch": 15.909090909090908,
      "eval_f1_score": 0.8571428571428571,
      "eval_loss": 0.40493202209472656,
      "eval_precision": 0.8486842105263158,
      "eval_recall": 0.8657718120805369,
      "eval_roc_auc": 0.9029668192937339,
      "eval_runtime": 0.4878,
      "eval_samples_per_second": 723.589,
      "eval_steps_per_second": 6.149,
      "step": 350
    },
    {
      "epoch": 18.181818181818183,
      "grad_norm": 1.1147843599319458,
      "learning_rate": 3.6e-05,
      "loss": 0.2654,
      "step": 400
    },
    {
      "epoch": 18.181818181818183,
      "eval_f1_score": 0.8304498269896193,
      "eval_loss": 0.4450823664665222,
      "eval_precision": 0.8571428571428571,
      "eval_recall": 0.8053691275167785,
      "eval_roc_auc": 0.9034058834598256,
      "eval_runtime": 0.4878,
      "eval_samples_per_second": 723.718,
      "eval_steps_per_second": 6.151,
      "step": 400
    },
    {
      "epoch": 20.454545454545453,
      "grad_norm": 7.004922866821289,
      "learning_rate": 3.3e-05,
      "loss": 0.2596,
      "step": 450
    },
    {
      "epoch": 20.454545454545453,
      "eval_f1_score": 0.8395904436860068,
      "eval_loss": 0.4173749089241028,
      "eval_precision": 0.8541666666666666,
      "eval_recall": 0.825503355704698,
      "eval_roc_auc": 0.9070438436931568,
      "eval_runtime": 0.4865,
      "eval_samples_per_second": 725.609,
      "eval_steps_per_second": 6.167,
      "step": 450
    },
    {
      "epoch": 22.727272727272727,
      "grad_norm": 2.1273648738861084,
      "learning_rate": 3e-05,
      "loss": 0.2366,
      "step": 500
    },
    {
      "epoch": 22.727272727272727,
      "eval_f1_score": 0.8142857142857143,
      "eval_loss": 0.4525018334388733,
      "eval_precision": 0.8702290076335878,
      "eval_recall": 0.7651006711409396,
      "eval_roc_auc": 0.9105563570218905,
      "eval_runtime": 0.4875,
      "eval_samples_per_second": 724.141,
      "eval_steps_per_second": 6.154,
      "step": 500
    },
    {
      "epoch": 25.0,
      "grad_norm": 4.955398082733154,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.2306,
      "step": 550
    },
    {
      "epoch": 25.0,
      "eval_f1_score": 0.8350877192982457,
      "eval_loss": 0.4550461769104004,
      "eval_precision": 0.875,
      "eval_recall": 0.7986577181208053,
      "eval_roc_auc": 0.9146333814213135,
      "eval_runtime": 0.487,
      "eval_samples_per_second": 724.913,
      "eval_steps_per_second": 6.161,
      "step": 550
    },
    {
      "epoch": 27.272727272727273,
      "grad_norm": 1.5066548585891724,
      "learning_rate": 2.4e-05,
      "loss": 0.2214,
      "step": 600
    },
    {
      "epoch": 27.272727272727273,
      "eval_f1_score": 0.8542372881355932,
      "eval_loss": 0.4234406054019928,
      "eval_precision": 0.863013698630137,
      "eval_recall": 0.8456375838926175,
      "eval_roc_auc": 0.9131280185661419,
      "eval_runtime": 0.487,
      "eval_samples_per_second": 724.849,
      "eval_steps_per_second": 6.16,
      "step": 600
    },
    {
      "epoch": 29.545454545454547,
      "grad_norm": 2.199934482574463,
      "learning_rate": 2.1e-05,
      "loss": 0.2007,
      "step": 650
    },
    {
      "epoch": 29.545454545454547,
      "eval_f1_score": 0.8406779661016949,
      "eval_loss": 0.4141705632209778,
      "eval_precision": 0.8493150684931506,
      "eval_recall": 0.8322147651006712,
      "eval_roc_auc": 0.9175186602270589,
      "eval_runtime": 0.4861,
      "eval_samples_per_second": 726.128,
      "eval_steps_per_second": 6.171,
      "step": 650
    },
    {
      "epoch": 31.818181818181817,
      "grad_norm": 3.5876011848449707,
      "learning_rate": 1.8e-05,
      "loss": 0.1869,
      "step": 700
    },
    {
      "epoch": 31.818181818181817,
      "eval_f1_score": 0.8533333333333334,
      "eval_loss": 0.42080163955688477,
      "eval_precision": 0.847682119205298,
      "eval_recall": 0.8590604026845637,
      "eval_roc_auc": 0.9163896380856803,
      "eval_runtime": 0.486,
      "eval_samples_per_second": 726.361,
      "eval_steps_per_second": 6.173,
      "step": 700
    },
    {
      "epoch": 34.09090909090909,
      "grad_norm": 2.6010570526123047,
      "learning_rate": 1.5e-05,
      "loss": 0.1791,
      "step": 750
    },
    {
      "epoch": 34.09090909090909,
      "eval_f1_score": 0.8655737704918033,
      "eval_loss": 0.405379056930542,
      "eval_precision": 0.8461538461538461,
      "eval_recall": 0.8859060402684564,
      "eval_roc_auc": 0.9218465784356771,
      "eval_runtime": 0.4871,
      "eval_samples_per_second": 724.696,
      "eval_steps_per_second": 6.159,
      "step": 750
    },
    {
      "epoch": 36.36363636363637,
      "grad_norm": 4.041784286499023,
      "learning_rate": 1.2e-05,
      "loss": 0.1666,
      "step": 800
    },
    {
      "epoch": 36.36363636363637,
      "eval_f1_score": 0.8709677419354839,
      "eval_loss": 0.4173583388328552,
      "eval_precision": 0.8385093167701864,
      "eval_recall": 0.9060402684563759,
      "eval_roc_auc": 0.9189612996299317,
      "eval_runtime": 0.4862,
      "eval_samples_per_second": 725.969,
      "eval_steps_per_second": 6.17,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 46,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9066711283712e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}