last-checkpoint/trainer_state.json

{
  "best_metric": 0.18951324487670584,
  "best_model_checkpoint": "training_dir/checkpoint-250",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 7.054202556610107,
      "learning_rate": 3e-05,
      "loss": 0.947,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.35882867132867136,
      "eval_f1": 0.18951324487670584,
      "eval_loss": 1.1078598499298096,
      "eval_precision": 0.12875801536749965,
      "eval_recall": 0.35882867132867136,
      "eval_runtime": 48.7697,
      "eval_samples_per_second": 46.914,
      "eval_steps_per_second": 5.864,
      "step": 250
    }
  ],
  "logging_steps": 500,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 417223879867872.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}