{
  "best_global_step": 2000,
  "best_metric": 0.9388425925925926,
  "best_model_checkpoint": "myocardial_pubmedbert_mps_final_v3/checkpoint-2000",
  "epoch": 0.7407407407407407,
  "eval_steps": 1000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 2.475142478942871,
      "learning_rate": 9.9e-08,
      "loss": 0.1439,
      "step": 100
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.806380271911621,
      "learning_rate": 1.99e-07,
      "loss": 0.1511,
      "step": 200
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.5451908111572266,
      "learning_rate": 2.9899999999999996e-07,
      "loss": 0.1491,
      "step": 300
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.704113483428955,
      "learning_rate": 3.99e-07,
      "loss": 0.153,
      "step": 400
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 4.833273887634277,
      "learning_rate": 4.99e-07,
      "loss": 0.149,
      "step": 500
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.2810375690460205,
      "learning_rate": 5.989999999999999e-07,
      "loss": 0.1582,
      "step": 600
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 9.05034065246582,
      "learning_rate": 6.989999999999999e-07,
      "loss": 0.1711,
      "step": 700
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 7.097633361816406,
      "learning_rate": 7.99e-07,
      "loss": 0.1419,
      "step": 800
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 10.607206344604492,
      "learning_rate": 8.99e-07,
      "loss": 0.1298,
      "step": 900
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.5295910835266113,
      "learning_rate": 9.989999999999999e-07,
      "loss": 0.1401,
      "step": 1000
    },
    {
      "epoch": 0.18518518518518517,
      "eval_accuracy": 0.9386111111111111,
      "eval_loss": 0.1337883323431015,
      "eval_runtime": 906.5981,
      "eval_samples_per_second": 47.651,
      "eval_steps_per_second": 1.489,
      "step": 1000
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 7.718695163726807,
      "learning_rate": 9.98132075471698e-07,
      "loss": 0.1463,
      "step": 1100
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.2934257984161377,
      "learning_rate": 9.962452830188678e-07,
      "loss": 0.1505,
      "step": 1200
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 4.265007495880127,
      "learning_rate": 9.943584905660378e-07,
      "loss": 0.1451,
      "step": 1300
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 8.984698295593262,
      "learning_rate": 9.924716981132075e-07,
      "loss": 0.1412,
      "step": 1400
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 6.165067672729492,
      "learning_rate": 9.905849056603772e-07,
      "loss": 0.1354,
      "step": 1500
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 14.949434280395508,
      "learning_rate": 9.886981132075472e-07,
      "loss": 0.1305,
      "step": 1600
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 5.017131805419922,
      "learning_rate": 9.86811320754717e-07,
      "loss": 0.147,
      "step": 1700
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 6.54106330871582,
      "learning_rate": 9.849245283018867e-07,
      "loss": 0.1435,
      "step": 1800
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 10.726076126098633,
      "learning_rate": 9.830377358490567e-07,
      "loss": 0.1347,
      "step": 1900
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 7.49448299407959,
      "learning_rate": 9.811509433962264e-07,
      "loss": 0.1539,
      "step": 2000
    },
    {
      "epoch": 0.37037037037037035,
      "eval_accuracy": 0.9388425925925926,
      "eval_loss": 0.13230355083942413,
      "eval_runtime": 839.9501,
      "eval_samples_per_second": 51.432,
      "eval_steps_per_second": 1.607,
      "step": 2000
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 6.918424129486084,
      "learning_rate": 9.792641509433961e-07,
      "loss": 0.1403,
      "step": 2100
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 13.528965950012207,
      "learning_rate": 9.77377358490566e-07,
      "loss": 0.166,
      "step": 2200
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 19.130395889282227,
      "learning_rate": 9.754905660377358e-07,
      "loss": 0.1436,
      "step": 2300
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 6.962574481964111,
      "learning_rate": 9.736037735849056e-07,
      "loss": 0.136,
      "step": 2400
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 3.4236555099487305,
      "learning_rate": 9.717169811320755e-07,
      "loss": 0.1409,
      "step": 2500
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 4.90040397644043,
      "learning_rate": 9.698301886792453e-07,
      "loss": 0.1341,
      "step": 2600
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.5071120262145996,
      "learning_rate": 9.67943396226415e-07,
      "loss": 0.1329,
      "step": 2700
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 5.357398509979248,
      "learning_rate": 9.660566037735848e-07,
      "loss": 0.1429,
      "step": 2800
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 6.533838748931885,
      "learning_rate": 9.641698113207547e-07,
      "loss": 0.1474,
      "step": 2900
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 6.865920066833496,
      "learning_rate": 9.622830188679245e-07,
      "loss": 0.1443,
      "step": 3000
    },
    {
      "epoch": 0.5555555555555556,
      "eval_accuracy": 0.9375462962962963,
      "eval_loss": 0.13121084868907928,
      "eval_runtime": 878.1919,
      "eval_samples_per_second": 49.192,
      "eval_steps_per_second": 1.537,
      "step": 3000
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 25.085233688354492,
      "learning_rate": 9.603962264150942e-07,
      "loss": 0.1256,
      "step": 3100
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 2.6678526401519775,
      "learning_rate": 9.585094339622642e-07,
      "loss": 0.1551,
      "step": 3200
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 2.9341561794281006,
      "learning_rate": 9.56622641509434e-07,
      "loss": 0.1515,
      "step": 3300
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 5.913675785064697,
      "learning_rate": 9.547358490566037e-07,
      "loss": 0.1433,
      "step": 3400
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.7116216421127319,
      "learning_rate": 9.528490566037735e-07,
      "loss": 0.1361,
      "step": 3500
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.6480686068534851,
      "learning_rate": 9.509622641509434e-07,
      "loss": 0.1358,
      "step": 3600
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 3.0181212425231934,
      "learning_rate": 9.490754716981132e-07,
      "loss": 0.1501,
      "step": 3700
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 2.563554048538208,
      "learning_rate": 9.47188679245283e-07,
      "loss": 0.1347,
      "step": 3800
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 5.095635414123535,
      "learning_rate": 9.453018867924528e-07,
      "loss": 0.1425,
      "step": 3900
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 7.968899250030518,
      "learning_rate": 9.434150943396227e-07,
      "loss": 0.143,
      "step": 4000
    },
    {
      "epoch": 0.7407407407407407,
      "eval_accuracy": 0.938587962962963,
      "eval_loss": 0.13063164055347443,
      "eval_runtime": 772.4302,
      "eval_samples_per_second": 55.927,
      "eval_steps_per_second": 1.748,
      "step": 4000
    }
  ],
  "logging_steps": 100,
  "max_steps": 54000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3680331767808e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}