{
  "best_metric": 0.7370958403644444,
  "best_model_checkpoint": "Rcarvalo/test_modernbert_finetuned_CARDS_Persona/checkpoint-1372",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1372,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1457725947521866,
      "grad_norm": 11.716080665588379,
      "learning_rate": 4.8542274052478136e-05,
      "loss": 1.3993,
      "step": 100
    },
    {
      "epoch": 0.2915451895043732,
      "grad_norm": 6.769674777984619,
      "learning_rate": 4.708454810495627e-05,
      "loss": 0.9699,
      "step": 200
    },
    {
      "epoch": 0.43731778425655976,
      "grad_norm": 14.352046012878418,
      "learning_rate": 4.5626822157434404e-05,
      "loss": 0.8483,
      "step": 300
    },
    {
      "epoch": 0.5830903790087464,
      "grad_norm": 5.891226291656494,
      "learning_rate": 4.416909620991254e-05,
      "loss": 0.7687,
      "step": 400
    },
    {
      "epoch": 0.7288629737609329,
      "grad_norm": 8.555354118347168,
      "learning_rate": 4.271137026239067e-05,
      "loss": 0.7151,
      "step": 500
    },
    {
      "epoch": 0.8746355685131195,
      "grad_norm": 8.797219276428223,
      "learning_rate": 4.1253644314868806e-05,
      "loss": 0.6659,
      "step": 600
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7097074007568871,
      "eval_loss": 0.8791285753250122,
      "eval_runtime": 5.569,
      "eval_samples_per_second": 218.89,
      "eval_steps_per_second": 27.474,
      "step": 686
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 2.60249662399292,
      "learning_rate": 3.979591836734694e-05,
      "loss": 0.6143,
      "step": 700
    },
    {
      "epoch": 1.1661807580174928,
      "grad_norm": 12.424664497375488,
      "learning_rate": 3.833819241982507e-05,
      "loss": 0.3599,
      "step": 800
    },
    {
      "epoch": 1.3119533527696792,
      "grad_norm": 9.500361442565918,
      "learning_rate": 3.688046647230321e-05,
      "loss": 0.3193,
      "step": 900
    },
    {
      "epoch": 1.4577259475218658,
      "grad_norm": 34.40837860107422,
      "learning_rate": 3.542274052478135e-05,
      "loss": 0.3518,
      "step": 1000
    },
    {
      "epoch": 1.6034985422740524,
      "grad_norm": 21.60414695739746,
      "learning_rate": 3.3965014577259475e-05,
      "loss": 0.3092,
      "step": 1100
    },
    {
      "epoch": 1.749271137026239,
      "grad_norm": 3.5961649417877197,
      "learning_rate": 3.250728862973761e-05,
      "loss": 0.3081,
      "step": 1200
    },
    {
      "epoch": 1.8950437317784257,
      "grad_norm": 10.914637565612793,
      "learning_rate": 3.104956268221574e-05,
      "loss": 0.2884,
      "step": 1300
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7370958403644444,
      "eval_loss": 0.8873788714408875,
      "eval_runtime": 5.5471,
      "eval_samples_per_second": 219.753,
      "eval_steps_per_second": 27.582,
      "step": 1372
    }
  ],
  "logging_steps": 100,
  "max_steps": 3430,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 7480627387957248.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}