{
  "best_metric": 0.5628694891929626,
  "best_model_checkpoint": "output_pipe/H3K4me3/origin/checkpoint-800",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 1840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 9.999856948852539,
      "learning_rate": 2.92122905027933e-05,
      "loss": 0.7052,
      "step": 100
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 6.555872917175293,
      "learning_rate": 2.753631284916201e-05,
      "loss": 0.6974,
      "step": 200
    },
    {
      "epoch": 0.43478260869565216,
      "eval_accuracy": 0.6519021739130435,
      "eval_f1": 0.6472859020981344,
      "eval_loss": 0.6252989768981934,
      "eval_matthews_correlation": 0.2982120567132538,
      "eval_precision": 0.6509352846293209,
      "eval_recall": 0.6472989417079502,
      "eval_runtime": 1.64,
      "eval_samples_per_second": 2243.962,
      "eval_steps_per_second": 35.367,
      "step": 200
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 10.895277976989746,
      "learning_rate": 2.5860335195530725e-05,
      "loss": 0.647,
      "step": 300
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 13.307287216186523,
      "learning_rate": 2.4184357541899442e-05,
      "loss": 0.6402,
      "step": 400
    },
    {
      "epoch": 0.8695652173913043,
      "eval_accuracy": 0.6584239130434782,
      "eval_f1": 0.6584236860388981,
      "eval_loss": 0.6169613003730774,
      "eval_matthews_correlation": 0.3220566655224521,
      "eval_precision": 0.6610448792984156,
      "eval_recall": 0.6610117879241085,
      "eval_runtime": 1.6414,
      "eval_samples_per_second": 2242.015,
      "eval_steps_per_second": 35.336,
      "step": 400
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 9.527493476867676,
      "learning_rate": 2.2508379888268156e-05,
      "loss": 0.5937,
      "step": 500
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 21.95737648010254,
      "learning_rate": 2.0832402234636874e-05,
      "loss": 0.5398,
      "step": 600
    },
    {
      "epoch": 1.3043478260869565,
      "eval_accuracy": 0.6809782608695653,
      "eval_f1": 0.6806272489346898,
      "eval_loss": 0.6053802371025085,
      "eval_matthews_correlation": 0.37370172922502976,
      "eval_precision": 0.6880450607585084,
      "eval_recall": 0.6856642523106775,
      "eval_runtime": 1.652,
      "eval_samples_per_second": 2227.623,
      "eval_steps_per_second": 35.109,
      "step": 600
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 17.107023239135742,
      "learning_rate": 1.9173184357541898e-05,
      "loss": 0.5213,
      "step": 700
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 12.411290168762207,
      "learning_rate": 1.7497206703910616e-05,
      "loss": 0.513,
      "step": 800
    },
    {
      "epoch": 1.7391304347826086,
      "eval_accuracy": 0.7048913043478261,
      "eval_f1": 0.7045338405632524,
      "eval_loss": 0.5628694891929626,
      "eval_matthews_correlation": 0.4101109337743351,
      "eval_precision": 0.7046674488480548,
      "eval_recall": 0.7054442205488696,
      "eval_runtime": 1.6506,
      "eval_samples_per_second": 2229.501,
      "eval_steps_per_second": 35.139,
      "step": 800
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 11.334113121032715,
      "learning_rate": 1.582122905027933e-05,
      "loss": 0.4965,
      "step": 900
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 28.086755752563477,
      "learning_rate": 1.4145251396648046e-05,
      "loss": 0.3209,
      "step": 1000
    },
    {
      "epoch": 2.1739130434782608,
      "eval_accuracy": 0.7029891304347826,
      "eval_f1": 0.7023614089231047,
      "eval_loss": 0.7348151206970215,
      "eval_matthews_correlation": 0.40508519181609787,
      "eval_precision": 0.7022438526861932,
      "eval_recall": 0.7028417804165564,
      "eval_runtime": 1.6525,
      "eval_samples_per_second": 2226.972,
      "eval_steps_per_second": 35.099,
      "step": 1000
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 21.236024856567383,
      "learning_rate": 1.246927374301676e-05,
      "loss": 0.2459,
      "step": 1100
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 27.03154754638672,
      "learning_rate": 1.0793296089385476e-05,
      "loss": 0.2465,
      "step": 1200
    },
    {
      "epoch": 2.608695652173913,
      "eval_accuracy": 0.7266304347826087,
      "eval_f1": 0.7261754894636794,
      "eval_loss": 0.6555567383766174,
      "eval_matthews_correlation": 0.45300551506446013,
      "eval_precision": 0.7261108931112572,
      "eval_recall": 0.726895301078929,
      "eval_runtime": 1.6486,
      "eval_samples_per_second": 2232.252,
      "eval_steps_per_second": 35.182,
      "step": 1200
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 24.729053497314453,
      "learning_rate": 9.117318435754191e-06,
      "loss": 0.2336,
      "step": 1300
    },
    {
      "epoch": 3.0434782608695654,
      "grad_norm": 8.527237892150879,
      "learning_rate": 7.441340782122905e-06,
      "loss": 0.1989,
      "step": 1400
    },
    {
      "epoch": 3.0434782608695654,
      "eval_accuracy": 0.7502717391304348,
      "eval_f1": 0.7498163710812544,
      "eval_loss": 0.9599674344062805,
      "eval_matthews_correlation": 0.5001928701951829,
      "eval_precision": 0.7496841522913477,
      "eval_recall": 0.7505093986723612,
      "eval_runtime": 1.6491,
      "eval_samples_per_second": 2231.585,
      "eval_steps_per_second": 35.172,
      "step": 1400
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 1.4311695098876953,
      "learning_rate": 5.76536312849162e-06,
      "loss": 0.0516,
      "step": 1500
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 25.26365089416504,
      "learning_rate": 4.106145251396648e-06,
      "loss": 0.0524,
      "step": 1600
    },
    {
      "epoch": 3.4782608695652173,
      "eval_accuracy": 0.7529891304347827,
      "eval_f1": 0.7529298550551656,
      "eval_loss": 1.589869737625122,
      "eval_matthews_correlation": 0.5091195396887124,
      "eval_precision": 0.7541927197975609,
      "eval_recall": 0.7549273499052958,
      "eval_runtime": 1.6464,
      "eval_samples_per_second": 2235.204,
      "eval_steps_per_second": 35.229,
      "step": 1600
    },
    {
      "epoch": 3.6956521739130435,
      "grad_norm": 26.048221588134766,
      "learning_rate": 2.430167597765363e-06,
      "loss": 0.0506,
      "step": 1700
    },
    {
      "epoch": 3.9130434782608696,
      "grad_norm": 32.529476165771484,
      "learning_rate": 7.541899441340783e-07,
      "loss": 0.0413,
      "step": 1800
    },
    {
      "epoch": 3.9130434782608696,
      "eval_accuracy": 0.748641304347826,
      "eval_f1": 0.7474285608287964,
      "eval_loss": 1.434490442276001,
      "eval_matthews_correlation": 0.494938242187782,
      "eval_precision": 0.7477221063315149,
      "eval_recall": 0.7472163942164571,
      "eval_runtime": 1.6473,
      "eval_samples_per_second": 2233.905,
      "eval_steps_per_second": 35.208,
      "step": 1800
    },
    {
      "epoch": 4.0,
      "step": 1840,
      "total_flos": 9283152131334144.0,
      "train_loss": 0.37002268653848897,
      "train_runtime": 187.7318,
      "train_samples_per_second": 627.257,
      "train_steps_per_second": 9.801
    }
  ],
  "logging_steps": 100,
  "max_steps": 1840,
  "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": 9283152131334144.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}