{
  "best_global_step": 630,
  "best_metric": 0.9989594172736732,
  "best_model_checkpoint": "/content/pubmedbert_telemedicine_model/checkpoint-630",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 630,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 6.141483783721924,
      "learning_rate": 1.9600000000000003e-06,
      "loss": 0.6913,
      "step": 50
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 5.5242719650268555,
      "learning_rate": 3.96e-06,
      "loss": 0.4234,
      "step": 100
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 7.910869598388672,
      "learning_rate": 5.9600000000000005e-06,
      "loss": 0.1772,
      "step": 150
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.15211565792560577,
      "learning_rate": 7.960000000000002e-06,
      "loss": 0.0432,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9937565036420395,
      "eval_f1": 0.9937563684276723,
      "eval_loss": 0.030338821932673454,
      "eval_precision": 0.993790669877271,
      "eval_recall": 0.9937565036420395,
      "eval_runtime": 1.735,
      "eval_samples_per_second": 553.887,
      "eval_steps_per_second": 35.158,
      "step": 210
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.12918557226657867,
      "learning_rate": 9.960000000000001e-06,
      "loss": 0.0145,
      "step": 250
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.770988941192627,
      "learning_rate": 1.196e-05,
      "loss": 0.0192,
      "step": 300
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.2780894637107849,
      "learning_rate": 1.396e-05,
      "loss": 0.0134,
      "step": 350
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.010402346029877663,
      "learning_rate": 1.5960000000000003e-05,
      "loss": 0.0062,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9968782518210197,
      "eval_f1": 0.9968782450604551,
      "eval_loss": 0.013902434147894382,
      "eval_precision": 0.9968803971851417,
      "eval_recall": 0.9968782518210197,
      "eval_runtime": 1.735,
      "eval_samples_per_second": 553.875,
      "eval_steps_per_second": 35.158,
      "step": 420
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.015549360774457455,
      "learning_rate": 1.796e-05,
      "loss": 0.0084,
      "step": 450
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.004298510495573282,
      "learning_rate": 1.9960000000000002e-05,
      "loss": 0.0005,
      "step": 500
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.005786629859358072,
      "learning_rate": 1.821818181818182e-05,
      "loss": 0.0081,
      "step": 550
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.08662544935941696,
      "learning_rate": 1.64e-05,
      "loss": 0.0185,
      "step": 600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9989594172736732,
      "eval_f1": 0.9989594172736732,
      "eval_loss": 0.008851713500916958,
      "eval_precision": 0.9989615806473247,
      "eval_recall": 0.9989594172736732,
      "eval_runtime": 1.8568,
      "eval_samples_per_second": 517.545,
      "eval_steps_per_second": 32.851,
      "step": 630
    }
  ],
  "logging_steps": 50,
  "max_steps": 1050,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 165710631553920.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}