trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 516,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.23052512109279633,
      "eval_runtime": 0.1581,
      "eval_samples_per_second": 189.779,
      "eval_steps_per_second": 12.652,
      "step": 43
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.18447847664356232,
      "eval_runtime": 0.1568,
      "eval_samples_per_second": 191.325,
      "eval_steps_per_second": 12.755,
      "step": 86
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.20011132955551147,
      "eval_runtime": 0.1565,
      "eval_samples_per_second": 191.703,
      "eval_steps_per_second": 12.78,
      "step": 129
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.2371898740530014,
      "eval_runtime": 0.1566,
      "eval_samples_per_second": 191.571,
      "eval_steps_per_second": 12.771,
      "step": 172
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.23354952037334442,
      "eval_runtime": 0.1573,
      "eval_samples_per_second": 190.773,
      "eval_steps_per_second": 12.718,
      "step": 215
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.28240805864334106,
      "eval_runtime": 0.1569,
      "eval_samples_per_second": 191.243,
      "eval_steps_per_second": 12.75,
      "step": 258
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.2836208641529083,
      "eval_runtime": 0.1566,
      "eval_samples_per_second": 191.566,
      "eval_steps_per_second": 12.771,
      "step": 301
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.29465165734291077,
      "eval_runtime": 0.1564,
      "eval_samples_per_second": 191.864,
      "eval_steps_per_second": 12.791,
      "step": 344
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.28824296593666077,
      "eval_runtime": 0.1565,
      "eval_samples_per_second": 191.641,
      "eval_steps_per_second": 12.776,
      "step": 387
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.30423295497894287,
      "eval_runtime": 0.1566,
      "eval_samples_per_second": 191.574,
      "eval_steps_per_second": 12.772,
      "step": 430
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.30508285760879517,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.057,
      "eval_steps_per_second": 12.804,
      "step": 473
    },
    {
      "epoch": 11.627906976744185,
      "grad_norm": 0.020239315927028656,
      "learning_rate": 1.550387596899225e-06,
      "loss": 0.0222,
      "step": 500
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.30229300260543823,
      "eval_runtime": 0.1566,
      "eval_samples_per_second": 191.527,
      "eval_steps_per_second": 12.768,
      "step": 516
    }
  ],
  "logging_steps": 500,
  "max_steps": 516,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 1329880738290048.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}