checkpoint-116/trainer_state.json

{
  "best_global_step": 116,
  "best_metric": 0.7213724329692548,
  "best_model_checkpoint": "artifacts/topic_model/checkpoint-116",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 116,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 3.192338466644287,
      "learning_rate": 1.9036697247706422e-05,
      "loss": 1.7422,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6614173228346457,
      "eval_loss": 1.518955945968628,
      "eval_macro_f1": 0.5115357643035457,
      "eval_runtime": 0.2774,
      "eval_samples_per_second": 457.755,
      "eval_steps_per_second": 28.835,
      "step": 58
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 6.166723251342773,
      "learning_rate": 1.674311926605505e-05,
      "loss": 1.3965,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7874015748031497,
      "eval_loss": 1.076490879058838,
      "eval_macro_f1": 0.7213724329692548,
      "eval_runtime": 0.2838,
      "eval_samples_per_second": 447.547,
      "eval_steps_per_second": 28.192,
      "step": 116
    }
  ],
  "logging_steps": 50,
  "max_steps": 464,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 146974386052584.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}