checkpoint-183/trainer_state.json

{
  "best_metric": 0.8602739726027397,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-160",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 183,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9617486338797814,
      "eval_accuracy": 0.4876712328767123,
      "eval_f1": 0.32440734699411816,
      "eval_loss": 1.1426137685775757,
      "eval_precision": 0.31998188610890976,
      "eval_recall": 0.4876712328767123,
      "eval_runtime": 1.5868,
      "eval_samples_per_second": 230.024,
      "eval_steps_per_second": 28.989,
      "step": 22
    },
    {
      "epoch": 1.9672131147540983,
      "eval_accuracy": 0.6876712328767123,
      "eval_f1": 0.6726372384593322,
      "eval_loss": 0.8035227060317993,
      "eval_precision": 0.6780882232356064,
      "eval_recall": 0.6876712328767123,
      "eval_runtime": 1.5591,
      "eval_samples_per_second": 234.103,
      "eval_steps_per_second": 29.503,
      "step": 45
    },
    {
      "epoch": 2.972677595628415,
      "eval_accuracy": 0.736986301369863,
      "eval_f1": 0.7179122961593137,
      "eval_loss": 0.5865945219993591,
      "eval_precision": 0.7266763525667637,
      "eval_recall": 0.736986301369863,
      "eval_runtime": 1.5049,
      "eval_samples_per_second": 242.544,
      "eval_steps_per_second": 30.567,
      "step": 68
    },
    {
      "epoch": 3.978142076502732,
      "eval_accuracy": 0.7945205479452054,
      "eval_f1": 0.7852674207057345,
      "eval_loss": 0.5180361270904541,
      "eval_precision": 0.7921658130880418,
      "eval_recall": 0.7945205479452054,
      "eval_runtime": 1.524,
      "eval_samples_per_second": 239.5,
      "eval_steps_per_second": 30.184,
      "step": 91
    },
    {
      "epoch": 4.983606557377049,
      "eval_accuracy": 0.7232876712328767,
      "eval_f1": 0.7299958784843185,
      "eval_loss": 0.6972417831420898,
      "eval_precision": 0.7954469760289924,
      "eval_recall": 0.7232876712328767,
      "eval_runtime": 1.5556,
      "eval_samples_per_second": 234.639,
      "eval_steps_per_second": 29.571,
      "step": 114
    },
    {
      "epoch": 5.989071038251366,
      "eval_accuracy": 0.8054794520547945,
      "eval_f1": 0.7958302021593314,
      "eval_loss": 0.5580042004585266,
      "eval_precision": 0.8052187633545131,
      "eval_recall": 0.8054794520547945,
      "eval_runtime": 1.5685,
      "eval_samples_per_second": 232.706,
      "eval_steps_per_second": 29.327,
      "step": 137
    },
    {
      "epoch": 6.994535519125683,
      "eval_accuracy": 0.8602739726027397,
      "eval_f1": 0.858393361953483,
      "eval_loss": 0.3853427767753601,
      "eval_precision": 0.8584473878727092,
      "eval_recall": 0.8602739726027397,
      "eval_runtime": 1.5792,
      "eval_samples_per_second": 231.123,
      "eval_steps_per_second": 29.128,
      "step": 160
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8301369863013699,
      "eval_f1": 0.8318234814039167,
      "eval_loss": 0.40903881192207336,
      "eval_precision": 0.8414951955847754,
      "eval_recall": 0.8301369863013699,
      "eval_runtime": 1.487,
      "eval_samples_per_second": 245.46,
      "eval_steps_per_second": 30.935,
      "step": 183
    }
  ],
  "logging_steps": 500,
  "max_steps": 220,
  "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": 2.654477240832e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}