checkpoint-122/trainer_state.json

{
  "best_metric": 0.7777777777777778,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-122",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9836065573770492,
      "eval_accuracy": 0.5637860082304527,
      "eval_f1": 0.49656016746502873,
      "eval_loss": 1.1263551712036133,
      "eval_precision": 0.5260403310011795,
      "eval_recall": 0.5637860082304527,
      "eval_runtime": 1.0189,
      "eval_samples_per_second": 238.499,
      "eval_steps_per_second": 30.426,
      "step": 15
    },
    {
      "epoch": 1.9672131147540983,
      "eval_accuracy": 0.654320987654321,
      "eval_f1": 0.6103087287397109,
      "eval_loss": 0.9297327399253845,
      "eval_precision": 0.6400077012574776,
      "eval_recall": 0.654320987654321,
      "eval_runtime": 1.0331,
      "eval_samples_per_second": 235.213,
      "eval_steps_per_second": 30.007,
      "step": 30
    },
    {
      "epoch": 2.9508196721311473,
      "eval_accuracy": 0.6707818930041153,
      "eval_f1": 0.6458358584237818,
      "eval_loss": 0.839500904083252,
      "eval_precision": 0.6700062294696597,
      "eval_recall": 0.6707818930041153,
      "eval_runtime": 1.0251,
      "eval_samples_per_second": 237.061,
      "eval_steps_per_second": 30.242,
      "step": 45
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7325102880658436,
      "eval_f1": 0.7023767955866722,
      "eval_loss": 0.7256261110305786,
      "eval_precision": 0.6980472218233514,
      "eval_recall": 0.7325102880658436,
      "eval_runtime": 1.0208,
      "eval_samples_per_second": 238.055,
      "eval_steps_per_second": 30.369,
      "step": 61
    },
    {
      "epoch": 4.983606557377049,
      "eval_accuracy": 0.7530864197530864,
      "eval_f1": 0.7360211171604085,
      "eval_loss": 0.6660245060920715,
      "eval_precision": 0.733383916927066,
      "eval_recall": 0.7530864197530864,
      "eval_runtime": 1.0191,
      "eval_samples_per_second": 238.453,
      "eval_steps_per_second": 30.42,
      "step": 76
    },
    {
      "epoch": 5.967213114754099,
      "eval_accuracy": 0.7448559670781894,
      "eval_f1": 0.7394169380703285,
      "eval_loss": 0.641394317150116,
      "eval_precision": 0.7510319299474755,
      "eval_recall": 0.7448559670781894,
      "eval_runtime": 1.0279,
      "eval_samples_per_second": 236.402,
      "eval_steps_per_second": 30.158,
      "step": 91
    },
    {
      "epoch": 6.950819672131147,
      "eval_accuracy": 0.7654320987654321,
      "eval_f1": 0.7521250625471124,
      "eval_loss": 0.5891531109809875,
      "eval_precision": 0.7457521964331709,
      "eval_recall": 0.7654320987654321,
      "eval_runtime": 1.0292,
      "eval_samples_per_second": 236.097,
      "eval_steps_per_second": 30.119,
      "step": 106
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7777777777777778,
      "eval_f1": 0.7704687718708882,
      "eval_loss": 0.5790427327156067,
      "eval_precision": 0.7665413510500082,
      "eval_recall": 0.7777777777777778,
      "eval_runtime": 1.0231,
      "eval_samples_per_second": 237.524,
      "eval_steps_per_second": 30.301,
      "step": 122
    }
  ],
  "logging_steps": 500,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 1.766619191808e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}