1/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 61,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 31.75,
      "learning_rate": 5e-05,
      "loss": 0.7563,
      "mean_token_accuracy": 0.8153301239013672,
      "num_tokens": 1252.0,
      "step": 5
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 21.5,
      "learning_rate": 5e-05,
      "loss": 1.1705,
      "mean_token_accuracy": 0.7389552474021912,
      "num_tokens": 2560.0,
      "step": 10
    },
    {
      "epoch": 0.2459016393442623,
      "grad_norm": 18.625,
      "learning_rate": 5e-05,
      "loss": 0.9639,
      "mean_token_accuracy": 0.7681733012199402,
      "num_tokens": 3972.0,
      "step": 15
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 19.25,
      "learning_rate": 5e-05,
      "loss": 0.9376,
      "mean_token_accuracy": 0.7716612458229065,
      "num_tokens": 5201.0,
      "step": 20
    },
    {
      "epoch": 0.4098360655737705,
      "grad_norm": 17.125,
      "learning_rate": 5e-05,
      "loss": 0.914,
      "mean_token_accuracy": 0.7721086025238038,
      "num_tokens": 6522.0,
      "step": 25
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 17.625,
      "learning_rate": 5e-05,
      "loss": 0.843,
      "mean_token_accuracy": 0.8011335134506226,
      "num_tokens": 7769.0,
      "step": 30
    },
    {
      "epoch": 0.5737704918032787,
      "grad_norm": 18.375,
      "learning_rate": 5e-05,
      "loss": 1.2051,
      "mean_token_accuracy": 0.7218420267105102,
      "num_tokens": 8996.0,
      "step": 35
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 17.75,
      "learning_rate": 5e-05,
      "loss": 0.931,
      "mean_token_accuracy": 0.7785208344459533,
      "num_tokens": 10370.0,
      "step": 40
    },
    {
      "epoch": 0.7377049180327869,
      "grad_norm": 17.0,
      "learning_rate": 5e-05,
      "loss": 0.791,
      "mean_token_accuracy": 0.8123364329338074,
      "num_tokens": 11731.0,
      "step": 45
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 23.5,
      "learning_rate": 5e-05,
      "loss": 0.9352,
      "mean_token_accuracy": 0.7726597785949707,
      "num_tokens": 12962.0,
      "step": 50
    },
    {
      "epoch": 0.9016393442622951,
      "grad_norm": 16.375,
      "learning_rate": 5e-05,
      "loss": 1.235,
      "mean_token_accuracy": 0.714318597316742,
      "num_tokens": 14334.0,
      "step": 55
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 19.75,
      "learning_rate": 5e-05,
      "loss": 1.2433,
      "mean_token_accuracy": 0.7244440078735351,
      "num_tokens": 15493.0,
      "step": 60
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.302091121673584,
      "eval_mean_token_accuracy": 0.5821103639900684,
      "eval_num_tokens": 15742.0,
      "eval_runtime": 0.4679,
      "eval_samples_per_second": 130.376,
      "eval_steps_per_second": 17.098,
      "step": 61
    }
  ],
  "logging_steps": 5,
  "max_steps": 61,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 12958910834688.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}