trainer_state.json

{
  "best_metric": 0.6359876614042939,
  "best_model_checkpoint": "model_checkpoints/fine-tuned_blog-authorship-attribution/microsoft/deberta-v3-small/checkpoint-1875",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 35.22766876220703,
      "learning_rate": 4.0106666666666673e-05,
      "loss": 1.6036,
      "step": 375
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.555,
      "eval_loss": 1.1462026834487915,
      "eval_macro_f1": 0.5353708602721241,
      "eval_macro_precision": 0.5497714189118279,
      "eval_macro_recall": 0.5549999999999999,
      "eval_micro_f1": 0.555,
      "eval_runtime": 282.8346,
      "eval_samples_per_second": 7.071,
      "eval_steps_per_second": 0.884,
      "step": 375
    },
    {
      "epoch": 2.0,
      "grad_norm": 39.075862884521484,
      "learning_rate": 3.0106666666666668e-05,
      "loss": 0.9511,
      "step": 750
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6065,
      "eval_loss": 0.9465224742889404,
      "eval_macro_f1": 0.5896716169178771,
      "eval_macro_precision": 0.5985288261029209,
      "eval_macro_recall": 0.6065,
      "eval_micro_f1": 0.6065,
      "eval_runtime": 282.8871,
      "eval_samples_per_second": 7.07,
      "eval_steps_per_second": 0.884,
      "step": 750
    },
    {
      "epoch": 3.0,
      "grad_norm": 23.99466323852539,
      "learning_rate": 2.010666666666667e-05,
      "loss": 0.6326,
      "step": 1125
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6185,
      "eval_loss": 0.9319701194763184,
      "eval_macro_f1": 0.6044739785737623,
      "eval_macro_precision": 0.6157976975878152,
      "eval_macro_recall": 0.6184999999999998,
      "eval_micro_f1": 0.6185,
      "eval_runtime": 282.892,
      "eval_samples_per_second": 7.07,
      "eval_steps_per_second": 0.884,
      "step": 1125
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.676905632019043,
      "learning_rate": 1.0106666666666668e-05,
      "loss": 0.4675,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6415,
      "eval_loss": 0.9401471614837646,
      "eval_macro_f1": 0.6023451748227971,
      "eval_macro_precision": 0.5992999443077366,
      "eval_macro_recall": 0.6415000000000001,
      "eval_micro_f1": 0.6415,
      "eval_runtime": 282.864,
      "eval_samples_per_second": 7.071,
      "eval_steps_per_second": 0.884,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "grad_norm": 67.77677917480469,
      "learning_rate": 1.0666666666666668e-07,
      "loss": 0.3708,
      "step": 1875
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.639,
      "eval_loss": 0.9551867842674255,
      "eval_macro_f1": 0.6359876614042939,
      "eval_macro_precision": 0.6469646011112227,
      "eval_macro_recall": 0.639,
      "eval_micro_f1": 0.639,
      "eval_runtime": 282.9465,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 0.884,
      "step": 1875
    }
  ],
  "logging_steps": 500,
  "max_steps": 1875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3974730485760000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}