checkpoint-200/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 2.202085256576538,
      "learning_rate": 2.75e-05,
      "loss": 0.7001,
      "step": 50
    },
    {
      "epoch": 0.5,
      "eval_electronics_AUC": 0.8274661508704062,
      "eval_electronics_accuracy": 0.5875,
      "eval_electronics_f1": 0.0,
      "eval_electronics_loss": 0.7029502987861633,
      "eval_electronics_macro_f1": 0.3700787401574803,
      "eval_electronics_micro_f1": 0.5875,
      "eval_electronics_precision": 0.0,
      "eval_electronics_recall": 0.0,
      "eval_electronics_runtime": 1.1511,
      "eval_electronics_samples_per_second": 347.485,
      "eval_electronics_specificity": 1.0,
      "eval_electronics_steps_per_second": 0.869,
      "step": 50
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.9589738845825195,
      "learning_rate": 2.5e-05,
      "loss": 0.6259,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_electronics_AUC": 0.8812894906511928,
      "eval_electronics_accuracy": 0.805,
      "eval_electronics_f1": 0.7914438502673797,
      "eval_electronics_loss": 0.44977375864982605,
      "eval_electronics_macro_f1": 0.804172629359042,
      "eval_electronics_micro_f1": 0.805,
      "eval_electronics_precision": 0.7081339712918661,
      "eval_electronics_recall": 0.896969696969697,
      "eval_electronics_runtime": 1.1287,
      "eval_electronics_samples_per_second": 354.379,
      "eval_electronics_specificity": 0.7404255319148936,
      "eval_electronics_steps_per_second": 0.886,
      "step": 100
    },
    {
      "epoch": 1.5,
      "grad_norm": 15.954824447631836,
      "learning_rate": 2.25e-05,
      "loss": 0.5285,
      "step": 150
    },
    {
      "epoch": 1.5,
      "eval_electronics_AUC": 0.8546228239845262,
      "eval_electronics_accuracy": 0.75,
      "eval_electronics_f1": 0.647887323943662,
      "eval_electronics_loss": 0.5688791275024414,
      "eval_electronics_macro_f1": 0.7270444371656295,
      "eval_electronics_micro_f1": 0.75,
      "eval_electronics_precision": 0.773109243697479,
      "eval_electronics_recall": 0.5575757575757576,
      "eval_electronics_runtime": 1.1417,
      "eval_electronics_samples_per_second": 350.348,
      "eval_electronics_specificity": 0.8851063829787233,
      "eval_electronics_steps_per_second": 0.876,
      "step": 150
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.80739426612854,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.492,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_electronics_AUC": 0.8878401031592521,
      "eval_electronics_accuracy": 0.79,
      "eval_electronics_f1": 0.7741935483870968,
      "eval_electronics_loss": 0.5164185762405396,
      "eval_electronics_macro_f1": 0.7889659330720531,
      "eval_electronics_micro_f1": 0.79,
      "eval_electronics_precision": 0.6956521739130435,
      "eval_electronics_recall": 0.8727272727272727,
      "eval_electronics_runtime": 1.1374,
      "eval_electronics_samples_per_second": 351.668,
      "eval_electronics_specificity": 0.7319148936170212,
      "eval_electronics_steps_per_second": 0.879,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 271637546496000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}