run-m68fs73f/checkpoint-63/trainer_state.json

{
  "best_global_step": 63,
  "best_metric": 1.1014227867126465,
  "best_model_checkpoint": "topic_classifier_model/run-m68fs73f/checkpoint-63",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 63,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.83,
      "eval_loss": 1.1014227867126465,
      "eval_runtime": 197.2915,
      "eval_samples_per_second": 5.069,
      "eval_steps_per_second": 0.319,
      "step": 63
    }
  ],
  "logging_steps": 500,
  "max_steps": 63,
  "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": 0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "_wandb": {
      "cli_version": "0.21.3",
      "m": [],
      "python_version": "3.12.11",
      "t": {
        "1": [
          1,
          2,
          3,
          5,
          11,
          12,
          41,
          49,
          51,
          53,
          71,
          98,
          100,
          105
        ],
        "12": "0.21.3",
        "13": "linux-x86_64",
        "3": [
          14
        ],
        "4": "3.12.11",
        "5": "0.21.3",
        "6": "4.56.1",
        "8": [
          1,
          12
        ]
      }
    },
    "assignments": {},
    "learning_rate": 9.257214581169088e-06,
    "metric": "eval/loss",
    "num_train_epochs": 1,
    "per_device_train_batch_size": 16,
    "seed": 28
  }
}