trainer_state.json

{
  "best_metric": 0.35069674253463745,
  "best_model_checkpoint": "danmaku-spam/checkpoint-192",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7799607072691552,
      "eval_loss": 0.4711815118789673,
      "eval_runtime": 0.3379,
      "eval_samples_per_second": 1506.525,
      "eval_steps_per_second": 23.678,
      "step": 32
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8271119842829077,
      "eval_loss": 0.3976481258869171,
      "eval_runtime": 0.3122,
      "eval_samples_per_second": 1630.28,
      "eval_steps_per_second": 25.623,
      "step": 64
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8428290766208252,
      "eval_loss": 0.3673166036605835,
      "eval_runtime": 0.3056,
      "eval_samples_per_second": 1665.848,
      "eval_steps_per_second": 26.182,
      "step": 96
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8212180746561886,
      "eval_loss": 0.389240026473999,
      "eval_runtime": 0.3579,
      "eval_samples_per_second": 1422.305,
      "eval_steps_per_second": 22.354,
      "step": 128
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8605108055009824,
      "eval_loss": 0.3535878360271454,
      "eval_runtime": 0.31,
      "eval_samples_per_second": 1641.821,
      "eval_steps_per_second": 25.805,
      "step": 160
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8506876227897839,
      "eval_loss": 0.35069674253463745,
      "eval_runtime": 0.3173,
      "eval_samples_per_second": 1604.32,
      "eval_steps_per_second": 25.215,
      "step": 192
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8506876227897839,
      "eval_loss": 0.37072867155075073,
      "eval_runtime": 0.3565,
      "eval_samples_per_second": 1427.644,
      "eval_steps_per_second": 22.438,
      "step": 224
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8467583497053045,
      "eval_loss": 0.37388625741004944,
      "eval_runtime": 0.3195,
      "eval_samples_per_second": 1593.016,
      "eval_steps_per_second": 25.038,
      "step": 256
    }
  ],
  "logging_steps": 500,
  "max_steps": 640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 83359892998512.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}