trainer_state.json

{
  "best_global_step": 5514,
  "best_metric": 0.861991895146672,
  "best_model_checkpoint": "outputs/hate-speech-detection/mbert/checkpoint-5514",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 5514,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.998911860718172,
      "grad_norm": 4.496480941772461,
      "learning_rate": 1.9996091589167148e-05,
      "loss": 0.4497,
      "step": 918
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8672093023255814,
      "eval_f1": 0.8381693329314983,
      "eval_loss": 0.38074544072151184,
      "eval_precision": 0.839596315015221,
      "eval_recall": 0.8672093023255814,
      "eval_runtime": 19.5248,
      "eval_samples_per_second": 220.233,
      "eval_steps_per_second": 6.914,
      "step": 919
    },
    {
      "epoch": 1.997823721436344,
      "grad_norm": 3.883493185043335,
      "learning_rate": 1.9982377977480694e-05,
      "loss": 0.3285,
      "step": 1836
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.871860465116279,
      "eval_f1": 0.8487258188734706,
      "eval_loss": 0.38101404905319214,
      "eval_precision": 0.8488176209662102,
      "eval_recall": 0.871860465116279,
      "eval_runtime": 19.6307,
      "eval_samples_per_second": 219.044,
      "eval_steps_per_second": 6.877,
      "step": 1838
    },
    {
      "epoch": 2.996735582154516,
      "grad_norm": 6.906253814697266,
      "learning_rate": 1.9958812963917564e-05,
      "loss": 0.2625,
      "step": 2754
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8690697674418605,
      "eval_f1": 0.8595973310447063,
      "eval_loss": 0.38094526529312134,
      "eval_precision": 0.8602939065897677,
      "eval_recall": 0.8690697674418605,
      "eval_runtime": 19.6152,
      "eval_samples_per_second": 219.218,
      "eval_steps_per_second": 6.882,
      "step": 2757
    },
    {
      "epoch": 3.995647442872688,
      "grad_norm": 5.721479415893555,
      "learning_rate": 1.992541980430111e-05,
      "loss": 0.2028,
      "step": 3672
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8455813953488373,
      "eval_f1": 0.8481157607486833,
      "eval_loss": 0.4412923753261566,
      "eval_precision": 0.8528228084873011,
      "eval_recall": 0.8455813953488373,
      "eval_runtime": 19.5818,
      "eval_samples_per_second": 219.592,
      "eval_steps_per_second": 6.894,
      "step": 3676
    },
    {
      "epoch": 4.99455930359086,
      "grad_norm": 2.1352882385253906,
      "learning_rate": 1.9882231453648264e-05,
      "loss": 0.1518,
      "step": 4590
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.858139534883721,
      "eval_f1": 0.8538781067265747,
      "eval_loss": 0.5418818593025208,
      "eval_precision": 0.8503660980046817,
      "eval_recall": 0.858139534883721,
      "eval_runtime": 19.6103,
      "eval_samples_per_second": 219.273,
      "eval_steps_per_second": 6.884,
      "step": 4595
    },
    {
      "epoch": 5.993471164309032,
      "grad_norm": 1.7267584800720215,
      "learning_rate": 1.982929053364693e-05,
      "loss": 0.1191,
      "step": 5508
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8748837209302326,
      "eval_f1": 0.861991895146672,
      "eval_loss": 0.5352126955986023,
      "eval_precision": 0.85848454601395,
      "eval_recall": 0.8748837209302326,
      "eval_runtime": 40.9448,
      "eval_samples_per_second": 105.02,
      "eval_steps_per_second": 3.297,
      "step": 5514
    }
  ],
  "logging_steps": 918,
  "max_steps": 91900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}