checkpoint-194/trainer_state.json

{
  "best_metric": 0.813953488372093,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-194",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 194,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9896907216494846,
      "eval_accuracy": 0.43410852713178294,
      "eval_f1": 0.2628116488581605,
      "eval_loss": 1.305585265159607,
      "eval_precision": 0.18845021332852593,
      "eval_recall": 0.43410852713178294,
      "eval_runtime": 1.6799,
      "eval_samples_per_second": 230.371,
      "eval_steps_per_second": 29.168,
      "step": 24
    },
    {
      "epoch": 1.9793814432989691,
      "eval_accuracy": 0.43410852713178294,
      "eval_f1": 0.2628116488581605,
      "eval_loss": 1.1732141971588135,
      "eval_precision": 0.18845021332852593,
      "eval_recall": 0.43410852713178294,
      "eval_runtime": 1.6247,
      "eval_samples_per_second": 238.193,
      "eval_steps_per_second": 30.159,
      "step": 48
    },
    {
      "epoch": 2.9690721649484537,
      "eval_accuracy": 0.6356589147286822,
      "eval_f1": 0.5935030180725367,
      "eval_loss": 0.9256265163421631,
      "eval_precision": 0.6651105917100348,
      "eval_recall": 0.6356589147286822,
      "eval_runtime": 1.639,
      "eval_samples_per_second": 236.125,
      "eval_steps_per_second": 29.897,
      "step": 72
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6563307493540051,
      "eval_f1": 0.6387188198872827,
      "eval_loss": 0.787194550037384,
      "eval_precision": 0.6724057806653244,
      "eval_recall": 0.6563307493540051,
      "eval_runtime": 1.6513,
      "eval_samples_per_second": 234.36,
      "eval_steps_per_second": 29.673,
      "step": 97
    },
    {
      "epoch": 4.989690721649485,
      "eval_accuracy": 0.7596899224806202,
      "eval_f1": 0.7447530111625,
      "eval_loss": 0.6241620182991028,
      "eval_precision": 0.7615023606202671,
      "eval_recall": 0.7596899224806202,
      "eval_runtime": 1.6695,
      "eval_samples_per_second": 231.805,
      "eval_steps_per_second": 29.35,
      "step": 121
    },
    {
      "epoch": 5.979381443298969,
      "eval_accuracy": 0.772609819121447,
      "eval_f1": 0.7744367108711326,
      "eval_loss": 0.5990303158760071,
      "eval_precision": 0.8035211915446686,
      "eval_recall": 0.772609819121447,
      "eval_runtime": 1.7017,
      "eval_samples_per_second": 227.425,
      "eval_steps_per_second": 28.795,
      "step": 145
    },
    {
      "epoch": 6.969072164948454,
      "eval_accuracy": 0.7906976744186046,
      "eval_f1": 0.7889441910896717,
      "eval_loss": 0.5285641551017761,
      "eval_precision": 0.8075499035137905,
      "eval_recall": 0.7906976744186046,
      "eval_runtime": 1.6621,
      "eval_samples_per_second": 232.838,
      "eval_steps_per_second": 29.481,
      "step": 169
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.813953488372093,
      "eval_f1": 0.8191057475344072,
      "eval_loss": 0.461563378572464,
      "eval_precision": 0.8344562802960127,
      "eval_recall": 0.813953488372093,
      "eval_runtime": 1.6538,
      "eval_samples_per_second": 234.004,
      "eval_steps_per_second": 29.628,
      "step": 194
    }
  ],
  "logging_steps": 500,
  "max_steps": 360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 2.81094402816e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}