run-4/checkpoint-839/trainer_state.json

{
  "best_metric": 0.3334433436393738,
  "best_model_checkpoint": "modernbert-financial-sentiment/run-4/checkpoint-839",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 839,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5959475566150179,
      "grad_norm": 8.621875762939453,
      "learning_rate": 2.5225093019019997e-05,
      "loss": 0.6134,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8748510131108462,
      "eval_f1": 0.8739883092458732,
      "eval_loss": 0.3334433436393738,
      "eval_precision": 0.8736840971108906,
      "eval_recall": 0.8748510131108462,
      "eval_runtime": 17.0678,
      "eval_samples_per_second": 98.314,
      "eval_steps_per_second": 12.304,
      "step": 839
    }
  ],
  "logging_steps": 500,
  "max_steps": 1678,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 681520416768000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "adam_epsilon": 1.0111063924919479e-08,
    "dropout": 0.14986636674008116,
    "learning_rate": 3.0727872305019286e-05,
    "lr_scheduler_type": "polynomial",
    "num_train_epochs": 2,
    "per_device_train_batch_size": 16,
    "warmup_ratio": 0.1440426494220562,
    "weight_decay": 0.09625464285160057
  }
}