trainer_state.json

{
  "best_global_step": 126,
  "best_metric": 0.8264642357826233,
  "best_model_checkpoint": "outputs\\meta-llama__Llama-3.2-1B\\amazon_13k\\run_0\\checkpoint-126",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1_macro": 0.6783075928688049,
      "eval_f1_micro": 0.7890295386314392,
      "eval_loss": 0.1833878755569458,
      "eval_runtime": 30.1882,
      "eval_samples_per_second": 16.563,
      "eval_steps_per_second": 4.141,
      "step": 63
    },
    {
      "epoch": 2.0,
      "eval_f1_macro": 0.7235337495803833,
      "eval_f1_micro": 0.8264642357826233,
      "eval_loss": 0.15523777902126312,
      "eval_runtime": 30.0805,
      "eval_samples_per_second": 16.622,
      "eval_steps_per_second": 4.156,
      "step": 126
    }
  ],
  "logging_steps": 500,
  "max_steps": 1260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 1.4378769774870528e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}