trainer_state.json

{
  "best_metric": 0.4026155173778534,
  "best_model_checkpoint": "phobert-base-v2-finetuned-cola/checkpoint-168",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 560,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7915254237288135,
      "eval_f1": 0.7893721715117984,
      "eval_loss": 0.47239404916763306,
      "eval_precision": 0.8028524325530298,
      "eval_recall": 0.7915254237288135,
      "eval_runtime": 1.8809,
      "eval_samples_per_second": 941.062,
      "eval_steps_per_second": 7.443,
      "step": 56
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8305084745762712,
      "eval_f1": 0.8304238301271201,
      "eval_loss": 0.40563058853149414,
      "eval_precision": 0.8314630699298234,
      "eval_recall": 0.8305084745762712,
      "eval_runtime": 1.9014,
      "eval_samples_per_second": 930.917,
      "eval_steps_per_second": 7.363,
      "step": 112
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8468926553672317,
      "eval_f1": 0.8468474301103891,
      "eval_loss": 0.4026155173778534,
      "eval_precision": 0.8471404512621079,
      "eval_recall": 0.8468926553672317,
      "eval_runtime": 1.8754,
      "eval_samples_per_second": 943.782,
      "eval_steps_per_second": 7.465,
      "step": 168
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.848587570621469,
      "eval_f1": 0.8485736509993659,
      "eval_loss": 0.40611279010772705,
      "eval_precision": 0.8488718847691179,
      "eval_recall": 0.848587570621469,
      "eval_runtime": 1.8854,
      "eval_samples_per_second": 938.79,
      "eval_steps_per_second": 7.425,
      "step": 224
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8564971751412429,
      "eval_f1": 0.8564870964602922,
      "eval_loss": 0.40367403626441956,
      "eval_precision": 0.8565317097754656,
      "eval_recall": 0.8564971751412429,
      "eval_runtime": 1.8903,
      "eval_samples_per_second": 936.352,
      "eval_steps_per_second": 7.406,
      "step": 280
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8508474576271187,
      "eval_f1": 0.8507729476716981,
      "eval_loss": 0.4181285500526428,
      "eval_precision": 0.8513274224982177,
      "eval_recall": 0.8508474576271187,
      "eval_runtime": 1.8867,
      "eval_samples_per_second": 938.139,
      "eval_steps_per_second": 7.42,
      "step": 336
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8502824858757062,
      "eval_f1": 0.8502669536796478,
      "eval_loss": 0.4214802384376526,
      "eval_precision": 0.8505908206321785,
      "eval_recall": 0.8502824858757062,
      "eval_runtime": 1.9061,
      "eval_samples_per_second": 928.618,
      "eval_steps_per_second": 7.345,
      "step": 392
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8536723163841808,
      "eval_f1": 0.8536290937217372,
      "eval_loss": 0.42303475737571716,
      "eval_precision": 0.8539268289850389,
      "eval_recall": 0.8536723163841808,
      "eval_runtime": 1.8896,
      "eval_samples_per_second": 936.69,
      "eval_steps_per_second": 7.409,
      "step": 448
    },
    {
      "epoch": 8.928571428571429,
      "grad_norm": 3.3562204837799072,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 0.3421,
      "step": 500
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8531073446327684,
      "eval_f1": 0.8530482335798589,
      "eval_loss": 0.42434096336364746,
      "eval_precision": 0.8534799563816656,
      "eval_recall": 0.8531073446327684,
      "eval_runtime": 1.8787,
      "eval_samples_per_second": 942.117,
      "eval_steps_per_second": 7.452,
      "step": 504
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8531073446327684,
      "eval_f1": 0.8530902740380235,
      "eval_loss": 0.42681607604026794,
      "eval_precision": 0.8531799918482982,
      "eval_recall": 0.8531073446327684,
      "eval_runtime": 1.8871,
      "eval_samples_per_second": 937.958,
      "eval_steps_per_second": 7.419,
      "step": 560
    }
  ],
  "logging_steps": 500,
  "max_steps": 560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 995766400116240.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}