checkpoint-149/trainer_state.json

{
  "best_metric": 0.889261744966443,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-130",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 149,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9664429530201343,
      "eval_accuracy": 0.7818791946308725,
      "eval_f1": 0.7264205130236912,
      "eval_loss": 0.669560968875885,
      "eval_precision": 0.689807639599501,
      "eval_recall": 0.7818791946308725,
      "eval_runtime": 0.9033,
      "eval_samples_per_second": 329.896,
      "eval_steps_per_second": 42.067,
      "step": 18
    },
    {
      "epoch": 1.9865771812080537,
      "eval_accuracy": 0.7751677852348994,
      "eval_f1": 0.7202681570933687,
      "eval_loss": 0.5067932605743408,
      "eval_precision": 0.684911313518696,
      "eval_recall": 0.7751677852348994,
      "eval_runtime": 0.907,
      "eval_samples_per_second": 328.546,
      "eval_steps_per_second": 41.895,
      "step": 37
    },
    {
      "epoch": 2.953020134228188,
      "eval_accuracy": 0.8087248322147651,
      "eval_f1": 0.7535236037076262,
      "eval_loss": 0.43038079142570496,
      "eval_precision": 0.7241626365959,
      "eval_recall": 0.8087248322147651,
      "eval_runtime": 0.8664,
      "eval_samples_per_second": 343.963,
      "eval_steps_per_second": 43.861,
      "step": 55
    },
    {
      "epoch": 3.9731543624161074,
      "eval_accuracy": 0.8523489932885906,
      "eval_f1": 0.8433916249277822,
      "eval_loss": 0.4109182059764862,
      "eval_precision": 0.8727817866814688,
      "eval_recall": 0.8523489932885906,
      "eval_runtime": 0.8712,
      "eval_samples_per_second": 342.059,
      "eval_steps_per_second": 43.618,
      "step": 74
    },
    {
      "epoch": 4.993288590604027,
      "eval_accuracy": 0.87248322147651,
      "eval_f1": 0.8717711524765707,
      "eval_loss": 0.3263051509857178,
      "eval_precision": 0.8718521382399975,
      "eval_recall": 0.87248322147651,
      "eval_runtime": 0.87,
      "eval_samples_per_second": 342.548,
      "eval_steps_per_second": 43.681,
      "step": 93
    },
    {
      "epoch": 5.959731543624161,
      "eval_accuracy": 0.8825503355704698,
      "eval_f1": 0.8824400125399595,
      "eval_loss": 0.3035907447338104,
      "eval_precision": 0.8824270850226767,
      "eval_recall": 0.8825503355704698,
      "eval_runtime": 0.8921,
      "eval_samples_per_second": 334.055,
      "eval_steps_per_second": 42.598,
      "step": 111
    },
    {
      "epoch": 6.97986577181208,
      "eval_accuracy": 0.889261744966443,
      "eval_f1": 0.8876321254746313,
      "eval_loss": 0.3046204149723053,
      "eval_precision": 0.8891935449502327,
      "eval_recall": 0.889261744966443,
      "eval_runtime": 0.894,
      "eval_samples_per_second": 333.317,
      "eval_steps_per_second": 42.504,
      "step": 130
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8758389261744967,
      "eval_f1": 0.8770158544888631,
      "eval_loss": 0.32443463802337646,
      "eval_precision": 0.8787167286554325,
      "eval_recall": 0.8758389261744967,
      "eval_runtime": 0.9094,
      "eval_samples_per_second": 327.69,
      "eval_steps_per_second": 41.786,
      "step": 149
    }
  ],
  "logging_steps": 500,
  "max_steps": 216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 2.16506368512e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}