run-7/checkpoint-2640/trainer_state.json

{
  "best_metric": 0.8942380591357089,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-multiclass-classification/run-7/checkpoint-2640",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 2640,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 6.107817649841309,
      "learning_rate": 2.4840825476810007e-05,
      "loss": 4.5331,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.740333586050038,
      "eval_loss": 2.2369935512542725,
      "eval_runtime": 91.726,
      "eval_samples_per_second": 28.76,
      "eval_steps_per_second": 1.799,
      "step": 660
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 6.087947845458984,
      "learning_rate": 1.9036894290639445e-05,
      "loss": 2.1934,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8351023502653525,
      "eval_loss": 1.15558922290802,
      "eval_runtime": 35.9351,
      "eval_samples_per_second": 73.41,
      "eval_steps_per_second": 4.592,
      "step": 1320
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 3.3006839752197266,
      "learning_rate": 1.3232963104468882e-05,
      "loss": 1.3094,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8771796815769523,
      "eval_loss": 0.8357464075088501,
      "eval_runtime": 35.8332,
      "eval_samples_per_second": 73.619,
      "eval_steps_per_second": 4.605,
      "step": 1980
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 4.960676193237305,
      "learning_rate": 7.42903191829832e-06,
      "loss": 0.9238,
      "step": 2000
    },
    {
      "epoch": 3.787878787878788,
      "grad_norm": 5.372833728790283,
      "learning_rate": 1.6251007321277576e-06,
      "loss": 0.7702,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8942380591357089,
      "eval_loss": 0.7534874677658081,
      "eval_runtime": 35.9466,
      "eval_samples_per_second": 73.387,
      "eval_steps_per_second": 4.59,
      "step": 2640
    }
  ],
  "logging_steps": 500,
  "max_steps": 2640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 503600392437760.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.064475666298057e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 16,
    "seed": 13
  }
}