checkpoint-1310/trainer_state.json

{
  "best_metric": 0.16112907230854034,
  "best_model_checkpoint": "YELP_full/checkpoint-393",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.17968642711639404,
      "eval_runtime": 78.2206,
      "eval_samples_per_second": 319.609,
      "eval_steps_per_second": 1.675,
      "step": 131
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.93844,
      "eval_loss": 0.1635778844356537,
      "eval_runtime": 78.3918,
      "eval_samples_per_second": 318.911,
      "eval_steps_per_second": 1.671,
      "step": 262
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.16112907230854034,
      "eval_runtime": 78.1143,
      "eval_samples_per_second": 320.044,
      "eval_steps_per_second": 1.677,
      "step": 393
    },
    {
      "epoch": 3.82,
      "grad_norm": 4.371647834777832,
      "learning_rate": 3.7099236641221374e-05,
      "loss": 0.1759,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.94228,
      "eval_loss": 0.18924400210380554,
      "eval_runtime": 78.0582,
      "eval_samples_per_second": 320.274,
      "eval_steps_per_second": 1.678,
      "step": 524
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.94408,
      "eval_loss": 0.17596399784088135,
      "eval_runtime": 78.0645,
      "eval_samples_per_second": 320.248,
      "eval_steps_per_second": 1.678,
      "step": 655
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.94128,
      "eval_loss": 0.22926613688468933,
      "eval_runtime": 78.0797,
      "eval_samples_per_second": 320.186,
      "eval_steps_per_second": 1.678,
      "step": 786
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.24049581587314606,
      "eval_runtime": 78.383,
      "eval_samples_per_second": 318.947,
      "eval_steps_per_second": 1.671,
      "step": 917
    },
    {
      "epoch": 7.63,
      "grad_norm": 3.099727153778076,
      "learning_rate": 1.4198473282442749e-05,
      "loss": 0.038,
      "step": 1000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.94356,
      "eval_loss": 0.25248077511787415,
      "eval_runtime": 78.171,
      "eval_samples_per_second": 319.812,
      "eval_steps_per_second": 1.676,
      "step": 1048
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.94368,
      "eval_loss": 0.2984617054462433,
      "eval_runtime": 79.1391,
      "eval_samples_per_second": 315.9,
      "eval_steps_per_second": 1.655,
      "step": 1179
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.94508,
      "eval_loss": 0.3094567358493805,
      "eval_runtime": 78.4753,
      "eval_samples_per_second": 318.572,
      "eval_steps_per_second": 1.669,
      "step": 1310
    }
  ],
  "logging_steps": 500,
  "max_steps": 1310,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.305063972569088e+17,
  "train_batch_size": 192,
  "trial_name": null,
  "trial_params": null
}