{
  "best_global_step": 500,
  "best_metric": 0.9595375722543352,
  "best_model_checkpoint": "resultados_beto_spam/checkpoint-500",
  "epoch": 4.0,
  "eval_steps": 100,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.989236354827881,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.5405,
      "step": 25
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.6037867069244385,
      "learning_rate": 1.3714285714285716e-05,
      "loss": 0.3262,
      "step": 50
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 8.116971015930176,
      "learning_rate": 1.9936507936507938e-05,
      "loss": 0.2236,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 18.044876098632812,
      "learning_rate": 1.9142857142857146e-05,
      "loss": 0.2458,
      "step": 100
    },
    {
      "epoch": 0.5714285714285714,
      "eval_accuracy": 0.9483870967741935,
      "eval_f1": 0.9069767441860465,
      "eval_loss": 0.15456445515155792,
      "eval_precision": 0.9285714285714286,
      "eval_recall": 0.8863636363636364,
      "eval_runtime": 0.647,
      "eval_samples_per_second": 479.113,
      "eval_steps_per_second": 15.455,
      "step": 100
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 7.314237594604492,
      "learning_rate": 1.834920634920635e-05,
      "loss": 0.1716,
      "step": 125
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 27.039167404174805,
      "learning_rate": 1.7555555555555556e-05,
      "loss": 0.1867,
      "step": 150
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.7663772106170654,
      "learning_rate": 1.6761904761904764e-05,
      "loss": 0.1497,
      "step": 175
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.15803247690200806,
      "learning_rate": 1.596825396825397e-05,
      "loss": 0.1079,
      "step": 200
    },
    {
      "epoch": 1.1428571428571428,
      "eval_accuracy": 0.9419354838709677,
      "eval_f1": 0.8977272727272727,
      "eval_loss": 0.1612335443496704,
      "eval_precision": 0.8977272727272727,
      "eval_recall": 0.8977272727272727,
      "eval_runtime": 0.6656,
      "eval_samples_per_second": 465.777,
      "eval_steps_per_second": 15.025,
      "step": 200
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 10.773611068725586,
      "learning_rate": 1.5174603174603176e-05,
      "loss": 0.0956,
      "step": 225
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.21190352737903595,
      "learning_rate": 1.4380952380952382e-05,
      "loss": 0.0767,
      "step": 250
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.2179877907037735,
      "learning_rate": 1.3587301587301589e-05,
      "loss": 0.0807,
      "step": 275
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 4.178826332092285,
      "learning_rate": 1.2793650793650794e-05,
      "loss": 0.0521,
      "step": 300
    },
    {
      "epoch": 1.7142857142857144,
      "eval_accuracy": 0.9612903225806452,
      "eval_f1": 0.9294117647058824,
      "eval_loss": 0.1485832780599594,
      "eval_precision": 0.9634146341463414,
      "eval_recall": 0.8977272727272727,
      "eval_runtime": 0.6744,
      "eval_samples_per_second": 459.643,
      "eval_steps_per_second": 14.827,
      "step": 300
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 22.12260627746582,
      "learning_rate": 1.2e-05,
      "loss": 0.1221,
      "step": 325
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.538419246673584,
      "learning_rate": 1.1206349206349207e-05,
      "loss": 0.143,
      "step": 350
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.5462950468063354,
      "learning_rate": 1.0412698412698415e-05,
      "loss": 0.0278,
      "step": 375
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.16447554528713226,
      "learning_rate": 9.61904761904762e-06,
      "loss": 0.0416,
      "step": 400
    },
    {
      "epoch": 2.2857142857142856,
      "eval_accuracy": 0.9580645161290322,
      "eval_f1": 0.9281767955801105,
      "eval_loss": 0.13364847004413605,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 0.9545454545454546,
      "eval_runtime": 0.9943,
      "eval_samples_per_second": 311.781,
      "eval_steps_per_second": 10.057,
      "step": 400
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.22453711926937103,
      "learning_rate": 8.825396825396827e-06,
      "loss": 0.0134,
      "step": 425
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.014733703806996346,
      "learning_rate": 8.031746031746033e-06,
      "loss": 0.0392,
      "step": 450
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 1.5988539457321167,
      "learning_rate": 7.238095238095239e-06,
      "loss": 0.0171,
      "step": 475
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.09800253808498383,
      "learning_rate": 6.444444444444445e-06,
      "loss": 0.0225,
      "step": 500
    },
    {
      "epoch": 2.857142857142857,
      "eval_accuracy": 0.9774193548387097,
      "eval_f1": 0.9595375722543352,
      "eval_loss": 0.10622350871562958,
      "eval_precision": 0.9764705882352941,
      "eval_recall": 0.9431818181818182,
      "eval_runtime": 0.7906,
      "eval_samples_per_second": 392.086,
      "eval_steps_per_second": 12.648,
      "step": 500
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.008765934966504574,
      "learning_rate": 5.650793650793651e-06,
      "loss": 0.0249,
      "step": 525
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.010630094446241856,
      "learning_rate": 4.857142857142858e-06,
      "loss": 0.0167,
      "step": 550
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.014191461727023125,
      "learning_rate": 4.063492063492064e-06,
      "loss": 0.0006,
      "step": 575
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.028532234951853752,
      "learning_rate": 3.2698412698412703e-06,
      "loss": 0.0131,
      "step": 600
    },
    {
      "epoch": 3.4285714285714284,
      "eval_accuracy": 0.9612903225806452,
      "eval_f1": 0.9333333333333333,
      "eval_loss": 0.19023045897483826,
      "eval_precision": 0.9130434782608695,
      "eval_recall": 0.9545454545454546,
      "eval_runtime": 0.8264,
      "eval_samples_per_second": 375.131,
      "eval_steps_per_second": 12.101,
      "step": 600
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.06592556834220886,
      "learning_rate": 2.507936507936508e-06,
      "loss": 0.0145,
      "step": 625
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 0.00781934428960085,
      "learning_rate": 1.7142857142857145e-06,
      "loss": 0.0142,
      "step": 650
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 13.090912818908691,
      "learning_rate": 9.206349206349208e-07,
      "loss": 0.0151,
      "step": 675
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.008091372437775135,
      "learning_rate": 1.26984126984127e-07,
      "loss": 0.0126,
      "step": 700
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9580645161290322,
      "eval_f1": 0.9273743016759777,
      "eval_loss": 0.169586643576622,
      "eval_precision": 0.9120879120879121,
      "eval_recall": 0.9431818181818182,
      "eval_runtime": 1.1321,
      "eval_samples_per_second": 273.838,
      "eval_steps_per_second": 8.833,
      "step": 700
    }
  ],
  "logging_steps": 25,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 733816733399040.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}